From 85699202e6c17a5e2cbb4d8fbc95e770c1ed533e Mon Sep 17 00:00:00 2001 From: Cat Flynn Date: Thu, 20 Mar 2025 23:31:24 +0000 Subject: [PATCH] cw2 --- ...e0038_coursework_tf_MCMQ7-checkpoint.ipynb | 1105 ++++++++++++++--- cw2/spce0038_coursework_tf_MCMQ7.ipynb | 1003 ++++++++++++--- 2 files changed, 1763 insertions(+), 345 deletions(-) diff --git a/cw2/.ipynb_checkpoints/spce0038_coursework_tf_MCMQ7-checkpoint.ipynb b/cw2/.ipynb_checkpoints/spce0038_coursework_tf_MCMQ7-checkpoint.ipynb index 945689f..f3c9312 100644 --- a/cw2/.ipynb_checkpoints/spce0038_coursework_tf_MCMQ7-checkpoint.ipynb +++ b/cw2/.ipynb_checkpoints/spce0038_coursework_tf_MCMQ7-checkpoint.ipynb @@ -67,7 +67,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "3593c649", "metadata": {}, "outputs": [], @@ -132,7 +132,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "id": "a32c7c90", "metadata": { "deletable": false, @@ -153,13 +153,13 @@ "name": "stderr", "output_type": "stream", "text": [ - "2025-03-14 14:07:37.610956: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2025-03-14 14:07:37.788469: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2025-03-14 14:07:37.950994: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", + "2025-03-20 22:24:16.798627: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", + "2025-03-20 22:24:16.801652: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", + "2025-03-20 22:24:16.811341: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n", - "E0000 00:00:1741961258.106221 71564 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", - "E0000 00:00:1741961258.153214 71564 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", - "2025-03-14 14:07:38.479758: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", + "E0000 00:00:1742509456.827236 468842 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", + "E0000 00:00:1742509456.832323 468842 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", + "2025-03-20 22:24:16.848642: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n" ] } @@ -174,7 +174,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 3, "id": "fad96611", "metadata": { "deletable": false, @@ -251,7 +251,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 4, "id": "f9c193a0", "metadata": { "deletable": false, @@ -272,38 +272,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "2025-03-14 14:44:13.164833: W external/local_tsl/tsl/platform/cloud/google_auth_provider.cc:184] All attempts to get a Google authentication bearer token failed, returning an empty token. Retrieving token from files failed with \"NOT_FOUND: Could not locate the credentials file.\". Retrieving token from GCE failed with \"FAILED_PRECONDITION: Error executing an HTTP request: libcurl code 6 meaning 'Couldn't resolve host name', error details: Could not resolve host: metadata.google.internal\".\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1mDownloading and preparing dataset 218.21 MiB (download: 218.21 MiB, generated: 221.83 MiB, total: 440.05 MiB) to /home/ktyl/tensorflow_datasets/tf_flowers/3.0.1...\u001b[0m\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/ktyl/.conda/envs/mlbd/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", - " from .autonotebook import tqdm as notebook_tqdm\n", - "Dl Completed...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:31<00:00, 6.22s/ file]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1mDataset tf_flowers downloaded and prepared to /home/ktyl/tensorflow_datasets/tf_flowers/3.0.1. Subsequent calls will reuse this data.\u001b[0m\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "W0000 00:00:1741963485.913699 71564 gpu_device.cc:2344] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n", + "W0000 00:00:1742509459.195582 468842 gpu_device.cc:2344] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n", "Skipping registering GPU devices...\n" ] } @@ -315,7 +284,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "id": "e438b1ef", "metadata": { "deletable": false, @@ -336,8 +305,8 @@ "name": "stderr", "output_type": "stream", "text": [ - "2025-03-14 14:44:46.016395: I tensorflow/core/kernels/data/tf_record_dataset_op.cc:376] The default buffer size is 262144, which is overridden by the user specified `buffer_size` of 8388608\n", - "2025-03-14 14:44:46.984183: I tensorflow/core/framework/local_rendezvous.cc:405] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence\n" + "2025-03-20 22:24:19.295704: I tensorflow/core/kernels/data/tf_record_dataset_op.cc:376] The default buffer size is 262144, which is overridden by the user specified `buffer_size` of 8388608\n", + "2025-03-20 22:24:20.423168: I tensorflow/core/framework/local_rendezvous.cc:405] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence\n" ] } ], @@ -369,7 +338,7 @@ }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 6, "id": "69bf403d", "metadata": { "deletable": false, @@ -475,7 +444,7 @@ }, { "cell_type": "code", - "execution_count": 63, + "execution_count": 7, "id": "2f2da49d", "metadata": { "deletable": false, @@ -520,7 +489,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "id": "5b886c27", "metadata": { "deletable": false, @@ -537,7 +506,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "rescale_and_resize defined.\n" + ] + } + ], "source": [ "check_var_defined('rescale_and_resize')" ] @@ -565,7 +542,7 @@ }, { "cell_type": "code", - "execution_count": 62, + "execution_count": 9, "id": "a880cd0d", "metadata": { "deletable": false, @@ -580,28 +557,16 @@ "task": false } }, - "outputs": [ - { - "ename": "TypeError", - "evalue": "Field elements must be 2- or 3-tuples, got ''", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", - "Cell \u001b[0;32mIn[62], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# YOUR CODE HERE\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m images_preprocessed \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mndarray\u001b[49m\u001b[43m(\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mrescale_and_resize\u001b[49m\u001b[43m(\u001b[49m\u001b[43mimg\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mimg\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mimages\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m()\n", - "\u001b[0;31mTypeError\u001b[0m: Field elements must be 2- or 3-tuples, got ''" - ] - } - ], + "outputs": [], "source": [ "# YOUR CODE HERE\n", - "images_preprocessed = np.ndarray((1,), [rescale_and_resize(img) for img in images])\n", - "raise NotImplementedError()" + "images_preprocessed = np.array([rescale_and_resize(img) for img in images])\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "id": "f767e9cf", "metadata": { "deletable": false, @@ -618,7 +583,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "images_preprocessed defined.\n" + ] + } + ], "source": [ "check_var_defined('images_preprocessed')\n", "assert type(images_preprocessed) == np.ndarray, \"Make sure to store your answer as a np.ndarray\"" @@ -649,7 +622,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "id": "e40efe42", "metadata": { "deletable": false, @@ -664,11 +637,22 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "target: 2, encoding: [0. 0. 1. 0. 0.]\n" + ] + } + ], "source": [ "def one_hot_encoding(target):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + " v = np.zeros(len(labels))\n", + " v[target] = 1\n", + " return v\n", + " #raise NotImplementedError()\n", "\n", "print(f\"target: {targets[0]}, encoding: {one_hot_encoding(targets[0])}\")" ] @@ -696,7 +680,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "id": "b91925ad", "metadata": { "deletable": false, @@ -714,12 +698,13 @@ "outputs": [], "source": [ "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "targets_preprocessed = np.array([one_hot_encoding(t) for t in targets])\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "id": "008bf36d", "metadata": { "deletable": false, @@ -736,7 +721,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "targets_preprocessed defined.\n" + ] + } + ], "source": [ "check_var_defined('targets_preprocessed')\n", "assert type(targets_preprocessed) == np.ndarray, \"Make sure to store your answer as a np.ndarray\"" @@ -785,7 +778,11 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The training dataset is for initially fitting the models to the data.\n", + "\n", + "The test dataset is for performing final, unbiased verification of the model once training is complete.\n", + "\n", + "The validation set is somewhat of a halfway point between the two. It is used for tuning the model while training, for example by detecting overfitting. Overfitting can be detected by measuring the model's error on the validation set per epoch. If the validation error increases between epochs, the model could be overfitting and this can be used to stop the training early before it gets worse." ] }, { @@ -811,7 +808,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "id": "5fb75b70", "metadata": { "deletable": false, @@ -826,18 +823,29 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Train samples: 2936, Validation samples: 367, Test samples: 367\n" + ] + } + ], "source": [ "tf.keras.utils.set_random_seed(371947)\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()\n", + "length = len(images_preprocessed)\n", + "x_train, x_val, x_test = np.split(images_preprocessed, [int(length*.8), int(length*.9)])\n", + "y_train, y_val, y_test = np.split(targets_preprocessed, [int(length*.8), int(length*.9)])\n", + "#raise NotImplementedError()\n", "\n", "print(f\"Train samples: {len(x_train)}, Validation samples: {len(x_test)}, Test samples: {len(x_val)}\")" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "id": "caaff270", "metadata": { "deletable": false, @@ -854,7 +862,20 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "x_train defined.\n", + "y_train defined.\n", + "x_val defined.\n", + "y_val defined.\n", + "x_test defined.\n", + "y_test defined.\n" + ] + } + ], "source": [ "check_var_defined('x_train')\n", "check_var_defined('y_train')\n", @@ -889,7 +910,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "id": "156ef4a4", "metadata": { "deletable": false, @@ -977,7 +998,13 @@ } }, "source": [ - "YOUR ANSWER HERE" + "A common problem with activation functions is that of vanishing gradients in lower layers, when gradients become very small and cease to be updated in training, or exploding gradients, in which case the training algorithm may not converge. We use different activation functions to avoid this problem. The choice of activation function depends on multiple factors, one of which is whether the data has negative values or not. In our case, it does not - we normalised the data into the range (0, 1)\n", + "\n", + "The convolutional layer should use a ReLU activation function to prevent vanishing gradients, as the function's gradient is never zero for positive values.\n", + "\n", + "The dense layer should also use ReLU, for the same reason as the convolutional layer. It could use Tanh if negative values were present.\n", + "\n", + "The activation function for the output layer depends on the problem type. In our case we are doing multi-class classification, so we should use Softmax to map predictions to probabilities The probabilities for each class will sum to 1." ] }, { @@ -1022,7 +1049,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "id": "b869ea33", "metadata": { "deletable": false, @@ -1038,18 +1065,41 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/ktyl/.conda/envs/mlbd/lib/python3.11/site-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", + " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" + ] + } + ], "source": [ "tf.keras.backend.clear_session()\n", "tf.keras.utils.set_random_seed(93612)\n", "\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_basic = tf.keras.models.Sequential([\n", + " tf.keras.layers.Conv2D(filters=8, kernel_size=(3,3), activation=\"relu\", input_shape=(224,224,3)),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=16, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Flatten(),\n", + " tf.keras.layers.Dense(32, activation=\"relu\"),\n", + " tf.keras.layers.Dense(5, activation=\"softmax\")\n", + "])\n", + "\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "id": "dfd1b4b1", "metadata": { "deletable": false, @@ -1066,7 +1116,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('model_basic')" ] @@ -1114,7 +1172,9 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Categorical Cross-Entropy (CCE) is an appropriate loss function because we are using one-hot encoding and the softmax looss function. One-hot encoding works well with the softmax activation function as we are comparing probabilities and one-hot produces a multi-dimensional vector.\n", + "\n", + "We can measure categorial accuracy as a metric since the dataset is one-hot encodded and relatively balanced. The metric measures the proportion of predictions matching one-hot labels." ] }, { @@ -1140,7 +1200,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "id": "0daef6f2", "metadata": { "deletable": false, @@ -1159,12 +1219,15 @@ "outputs": [], "source": [ "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_basic.compile(loss=\"categorical_crossentropy\",\n", + " optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n", + " metrics=[tf.keras.metrics.CategoricalAccuracy()])\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "id": "b3f30c12", "metadata": { "deletable": false, @@ -1181,7 +1244,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('model_basic')" ] @@ -1209,7 +1280,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "id": "5f355c96", "metadata": { "deletable": false, @@ -1225,16 +1296,46 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 216ms/step - categorical_accuracy: 0.3034 - loss: 1.5835 - val_categorical_accuracy: 0.3842 - val_loss: 1.4783\n", + "Epoch 2/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 201ms/step - categorical_accuracy: 0.4216 - loss: 1.3884 - val_categorical_accuracy: 0.4741 - val_loss: 1.3093\n", + "Epoch 3/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 199ms/step - categorical_accuracy: 0.4820 - loss: 1.2396 - val_categorical_accuracy: 0.4932 - val_loss: 1.2155\n", + "Epoch 4/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 199ms/step - categorical_accuracy: 0.5169 - loss: 1.1568 - val_categorical_accuracy: 0.4932 - val_loss: 1.1751\n", + "Epoch 5/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 198ms/step - categorical_accuracy: 0.5300 - loss: 1.1089 - val_categorical_accuracy: 0.5177 - val_loss: 1.1498\n", + "Epoch 6/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 198ms/step - categorical_accuracy: 0.5450 - loss: 1.0736 - val_categorical_accuracy: 0.5259 - val_loss: 1.1298\n", + "Epoch 7/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 199ms/step - categorical_accuracy: 0.5634 - loss: 1.0433 - val_categorical_accuracy: 0.5368 - val_loss: 1.1149\n", + "Epoch 8/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 206ms/step - categorical_accuracy: 0.5852 - loss: 1.0178 - val_categorical_accuracy: 0.5450 - val_loss: 1.0949\n", + "Epoch 9/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 206ms/step - categorical_accuracy: 0.5967 - loss: 0.9953 - val_categorical_accuracy: 0.5559 - val_loss: 1.0862\n", + "Epoch 10/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 199ms/step - categorical_accuracy: 0.6108 - loss: 0.9734 - val_categorical_accuracy: 0.5613 - val_loss: 1.0745\n" + ] + } + ], "source": [ "tf.keras.utils.set_random_seed(47290)\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "history_basic = model_basic.fit(x_train, y_train, epochs=10,\n", + " validation_data=(x_val, y_val),\n", + " batch_size=32)\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "id": "d123574b", "metadata": { "deletable": false, @@ -1251,7 +1352,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "history_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('history_basic')" ] @@ -1279,7 +1388,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "id": "38bb58e0", "metadata": { "deletable": false, @@ -1295,11 +1404,48 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "def plot_metrics(history):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + " plt.figure()\n", + " plt.plot(history.history['loss'], label='Training Loss')\n", + " plt.plot(history.history['val_loss'], label='Validation Loss')\n", + " plt.xlabel('Epochs')\n", + " plt.ylabel('Loss')\n", + " plt.title('Training vs. Validation Loss')\n", + " plt.legend()\n", + " \n", + " plt.figure()\n", + " plt.plot(history.history['categorical_accuracy'], label='Categorical Accuracy')\n", + " plt.plot(history.history['val_categorical_accuracy'], label='Validation Categorical Accuracy')\n", + " plt.xlabel('Epochs')\n", + " plt.ylabel('Categorical Accuracy')\n", + " plt.title('Training vs. Validation Categorical Accuracy')\n", + " \n", + " plt.show()\n", + " #raise NotImplementedError()\n", " \n", "plot_metrics(history_basic)" ] @@ -1343,7 +1489,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The loss decreased over time and the accuracy increased as desired. However in both cases the effect was greater for the training data than for the validation set." ] }, { @@ -1385,7 +1531,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The difference between the training and validation sets for the loss and accuracy would increase. This would imply overfitting of the model as it becomes increasingly better at predicting samples from the training set than the validation set." ] }, { @@ -1411,7 +1557,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "id": "f22e89cb", "metadata": { "deletable": false, @@ -1430,7 +1576,9 @@ "source": [ "def model_predict(model, x):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + " predicted_targets_one_hot = model.predict(x)\n", + " predicted_targets = np.array([np.where(one_hot==np.max(one_hot))[0][0] for one_hot in predicted_targets_one_hot])\n", + " #raise NotImplementedError()\n", " return predicted_targets" ] }, @@ -1459,7 +1607,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "id": "3565c7b9", "metadata": { "deletable": false, @@ -1474,15 +1622,25 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step \n" + ] + } + ], "source": [ "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "test_targets = np.array([np.where(one_hot==1)[0][0] for one_hot in y_test])\n", + "test_targets_basic = np.array(model_predict(model_basic, x_test))\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "id": "a7f97fbb", "metadata": { "deletable": false, @@ -1499,7 +1657,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "test_targets defined.\n", + "test_targets_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('test_targets')\n", "check_var_defined('test_targets_basic')\n", @@ -1531,7 +1698,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "id": "c5047120", "metadata": { "deletable": false, @@ -1546,11 +1713,53 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average Recall: 0.618, Average Precision 0.642\n" + ] + } + ], "source": [ "def average_recall_precision(y, y_predict):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + "\n", + " precision = 0\n", + " recall = 0\n", + " \n", + " classes = set(y)\n", + " \n", + " for c in classes:\n", + " true_positives = 0\n", + " false_positives = 0\n", + " false_negatives = 0\n", + "\n", + " for truth, prediction in zip(y, y_predict):\n", + "\n", + " # Element is irrelevant for this class\n", + " if truth != c and prediction != c:\n", + " continue\n", + "\n", + " if truth == prediction:\n", + " true_positives += 1\n", + " elif truth == c:\n", + " false_negatives += 1\n", + " elif prediction == c:\n", + " false_positives += 1\n", + "\n", + " \n", + " precision_class = true_positives / (true_positives + false_positives) \n", + " recall_class = true_positives / (true_positives + false_negatives)\n", + " \n", + " precision += precision_class\n", + " recall += recall_class\n", + " \n", + " precision /= len(classes)\n", + " recall /= len(classes)\n", + " \n", + " #raise NotImplementedError()\n", "\n", " print(f\"Average Recall: {recall:.3f}, Average Precision {precision:0.3f}\")\n", " return recall, precision\n", @@ -1560,7 +1769,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "id": "5d9aae79", "metadata": { "deletable": false, @@ -1577,7 +1786,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "recall_basic defined.\n", + "precision_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('recall_basic')\n", "check_var_defined('precision_basic')" @@ -1628,7 +1846,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "id": "1b4795f7", "metadata": { "deletable": false, @@ -1644,13 +1862,27 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n", "\n", "def plot_confusion_matrix(y, y_pred, title=\"\"):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + " cm = confusion_matrix(y, y_pred, normalize=\"true\") * 100\n", + " display = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=labels)\n", + " display.plot(cmap=\"Greens\", values_format=\".1f\")\n", + " #raise NotImplementedError()\n", " plt.title(title)\n", " plt.show()\n", "\n", @@ -1696,7 +1928,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The average recall and precision are balanced, suggesting the model is equally good at minimising false positives as false negatives. Some information is lost in these averages, as we can see from the confusion matrix that the model performs much better for the sunflowers class as for the others with >92% accuracy. Roses are frequently misidentified as tulips, suggesting the model's precision for roses may be low." ] }, { @@ -1742,7 +1974,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Dropout layers set a random amount of the training data to zero in each epoch, forcing the model to generalise by providing effectively different training data each time. It becomes harder for the model to fit specifically to instances in the training data because it cannot see all of the training data at once." ] }, { @@ -1786,7 +2018,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Data augmentation is the process of applying small variations to the training data, for example rotating, cropping, flipping training or slightly altering the colours. This similarly limits the model's ability to fit specifically to the training data as it is operating on a modified version, instead of the training data itself, forcing it to generalise." ] }, { @@ -1812,7 +2044,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "id": "cae90829", "metadata": { "deletable": false, @@ -1828,18 +2060,45 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/ktyl/.conda/envs/mlbd/lib/python3.11/site-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", + " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" + ] + } + ], "source": [ "tf.keras.backend.clear_session()\n", "tf.keras.utils.set_random_seed(48263)\n", "\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_dropout = tf.keras.models.Sequential([\n", + " tf.keras.layers.RandomZoom(0.1, seed=42),\n", + " tf.keras.layers.RandomRotation(0.1, seed=42),\n", + " tf.keras.layers.RandomFlip(\"horizontal\", seed=42),\n", + " tf.keras.layers.Conv2D(filters=8, kernel_size=(3,3), activation=\"relu\", input_shape=(224,224,3)),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=16, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Flatten(),\n", + " tf.keras.layers.Dense(32, activation=\"relu\"),\n", + " tf.keras.layers.Dropout(0.5),\n", + " tf.keras.layers.Dense(5, activation=\"softmax\")\n", + "])\n", + "\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "id": "77868aae", "metadata": { "deletable": false, @@ -1856,12 +2115,230 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model_dropout defined.\n" + ] + }, + { + "data": { + "text/html": [ + "
Model: \"sequential\"\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1mModel: \"sequential\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ random_zoom (RandomZoom)        │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ random_rotation                 │ ?                      │   0 (unbuilt) │\n",
+       "│ (RandomRotation)                │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ random_flip (RandomFlip)        │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d (Conv2D)                 │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d (MaxPooling2D)    │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_1 (Conv2D)               │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_1 (MaxPooling2D)  │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_2 (Conv2D)               │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_2 (MaxPooling2D)  │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_3 (Conv2D)               │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_3 (MaxPooling2D)  │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten (Flatten)               │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (Dense)                   │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (Dropout)               │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (Dense)                 │ ?                      │   0 (unbuilt) │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ random_zoom (\u001b[38;5;33mRandomZoom\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ random_rotation │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "│ (\u001b[38;5;33mRandomRotation\u001b[0m) │ │ │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ random_flip (\u001b[38;5;33mRandomFlip\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 0 (0.00 B)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 0 (0.00 B)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 0 (0.00 B)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "check_var_defined('model_dropout')\n", "model_dropout.summary()" ] }, + { + "cell_type": "code", + "execution_count": 32, + "id": "92ec2689", + "metadata": { + "deletable": false, + "nbgrader": { + "cell_type": "code", + "checksum": "c89d459ee4ecefb767369c54929ecfb0", + "grade": true, + "grade_id": "cell-82fcca9814ec3c0e", + "locked": false, + "points": 1, + "schema_version": 3, + "solution": true, + "task": false + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 258ms/step - categorical_accuracy: 0.2455 - loss: 1.6014 - val_categorical_accuracy: 0.2916 - val_loss: 1.5391\n", + "Epoch 2/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 264ms/step - categorical_accuracy: 0.3000 - loss: 1.5297 - val_categorical_accuracy: 0.3379 - val_loss: 1.4781\n", + "Epoch 3/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 254ms/step - categorical_accuracy: 0.3400 - loss: 1.4764 - val_categorical_accuracy: 0.3515 - val_loss: 1.4463\n", + "Epoch 4/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 254ms/step - categorical_accuracy: 0.3607 - loss: 1.4422 - val_categorical_accuracy: 0.4278 - val_loss: 1.3648\n", + "Epoch 5/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 256ms/step - categorical_accuracy: 0.3780 - loss: 1.3957 - val_categorical_accuracy: 0.4741 - val_loss: 1.3091\n", + "Epoch 6/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.4264 - loss: 1.3473 - val_categorical_accuracy: 0.5041 - val_loss: 1.2634\n", + "Epoch 7/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.4359 - loss: 1.3280 - val_categorical_accuracy: 0.4905 - val_loss: 1.2468\n", + "Epoch 8/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 255ms/step - categorical_accuracy: 0.4456 - loss: 1.3061 - val_categorical_accuracy: 0.5259 - val_loss: 1.2070\n", + "Epoch 9/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.4730 - loss: 1.2948 - val_categorical_accuracy: 0.5259 - val_loss: 1.1895\n", + "Epoch 10/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 254ms/step - categorical_accuracy: 0.4730 - loss: 1.2780 - val_categorical_accuracy: 0.5232 - val_loss: 1.1882\n", + "Epoch 11/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.4722 - loss: 1.2699 - val_categorical_accuracy: 0.5668 - val_loss: 1.1537\n", + "Epoch 12/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.5036 - loss: 1.2272 - val_categorical_accuracy: 0.5804 - val_loss: 1.1287\n", + "Epoch 13/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.5042 - loss: 1.2143 - val_categorical_accuracy: 0.5777 - val_loss: 1.1289\n", + "Epoch 14/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.5186 - loss: 1.2249 - val_categorical_accuracy: 0.5858 - val_loss: 1.1071\n", + "Epoch 15/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.5055 - loss: 1.1896 - val_categorical_accuracy: 0.5777 - val_loss: 1.1020\n", + "Epoch 16/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.5239 - loss: 1.1767 - val_categorical_accuracy: 0.5913 - val_loss: 1.0925\n", + "Epoch 17/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.5264 - loss: 1.1780 - val_categorical_accuracy: 0.5804 - val_loss: 1.0838\n", + "Epoch 18/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 258ms/step - categorical_accuracy: 0.5320 - loss: 1.1648 - val_categorical_accuracy: 0.5967 - val_loss: 1.0745\n", + "Epoch 19/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.5469 - loss: 1.1741 - val_categorical_accuracy: 0.5940 - val_loss: 1.0532\n", + "Epoch 20/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 254ms/step - categorical_accuracy: 0.5266 - loss: 1.1739 - val_categorical_accuracy: 0.5967 - val_loss: 1.0518\n" + ] + } + ], + "source": [ + "tf.keras.utils.set_random_seed(103745)\n", + "# YOUR CODE HERE\n", + "model_dropout.compile(loss=\"categorical_crossentropy\",\n", + " optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n", + " metrics=[tf.keras.metrics.CategoricalAccuracy()])\n", + "\n", + "history_dropout = model_dropout.fit(x_train, y_train, epochs=20,\n", + " validation_data=(x_val, y_val),\n", + " batch_size=32)\n", + "#raise NotImplementedError()" + ] + }, { "cell_type": "markdown", "id": "6778a133", @@ -1885,32 +2362,7 @@ }, { "cell_type": "code", - "execution_count": null, - "id": "92ec2689", - "metadata": { - "deletable": false, - "nbgrader": { - "cell_type": "code", - "checksum": "c89d459ee4ecefb767369c54929ecfb0", - "grade": true, - "grade_id": "cell-82fcca9814ec3c0e", - "locked": false, - "points": 1, - "schema_version": 3, - "solution": true, - "task": false - } - }, - "outputs": [], - "source": [ - "tf.keras.utils.set_random_seed(103745)\n", - "# YOUR CODE HERE\n", - "raise NotImplementedError()" - ] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 33, "id": "5048652c", "metadata": { "deletable": false, @@ -1927,14 +2379,22 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "history_dropout defined.\n" + ] + } + ], "source": [ "check_var_defined('history_dropout')" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "id": "128cc76b", "metadata": { "deletable": false, @@ -1950,7 +2410,28 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plot_metrics(history_dropout)" ] @@ -1994,7 +2475,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "While the accuracy is lower and the loss higher than the basic model despite more time training, we can see from the plots that the training and validation loss and accuracy diverge much more slowly. This suggests the model is less susceptible to overfitting, so we are likely to get a better model with more training." ] }, { @@ -2036,7 +2517,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Each epoch has less training data to work from, so the model takes longer to learn class features with the same learning rate." ] }, { @@ -2062,7 +2543,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 35, "id": "b5d2ea24", "metadata": { "deletable": false, @@ -2078,7 +2559,26 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step \n", + "Average Recall: 0.685, Average Precision 0.682\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "test_targets_dropout = model_predict(model_dropout, x_test)\n", "recall_dropout, precision_dropout = average_recall_precision(test_targets, test_targets_dropout) \n", @@ -2087,7 +2587,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 36, "id": "dbae38a3", "metadata": { "deletable": false, @@ -2104,7 +2604,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "test_targets_dropout defined.\n", + "recall_dropout defined.\n" + ] + } + ], "source": [ "check_var_defined('test_targets_dropout')\n", "check_var_defined('recall_dropout')" @@ -2112,7 +2621,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 37, "id": "98f7bbc4", "metadata": { "deletable": false, @@ -2129,7 +2638,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "test_targets_dropout defined.\n", + "precision_dropout defined.\n" + ] + } + ], "source": [ "check_var_defined('test_targets_dropout')\n", "check_var_defined('precision_dropout')" @@ -2174,7 +2692,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The model is more precise and has better recall than the previous model, as we can see by a lower proportion of misidentifications for example mistaking roses for tulips as before. However, the difference is not enormous - more training may yield better results." ] }, { @@ -2220,7 +2738,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Transfer learning allows us to use a pre-trained model which saves time by using weights that have already been found and reduces overfitting as the model will be more general than our dataset. " ] }, { @@ -2246,7 +2764,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "id": "152fe58b", "metadata": { "deletable": false, @@ -2262,7 +2780,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Output shape of the MobileNet: (None, 7, 7, 1024)\n" + ] + } + ], "source": [ "mobilenet = tf.keras.applications.mobilenet.MobileNet(\n", " input_shape=(224, 224, 3),\n", @@ -2299,7 +2825,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 39, "id": "6427f088", "metadata": { "deletable": false, @@ -2321,12 +2847,21 @@ "tf.keras.utils.set_random_seed(387453)\n", "\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_mobilenet = tf.keras.models.Sequential([\n", + " mobilenet,\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Flatten(),\n", + " tf.keras.layers.Dense(32, activation=\"relu\"),\n", + " tf.keras.layers.Dropout(0.5),\n", + " tf.keras.layers.Dense(5, activation=\"softmax\")\n", + "])\n", + "\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 40, "id": "27b1a82a", "metadata": { "deletable": false, @@ -2343,7 +2878,108 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model_mobilenet defined.\n" + ] + }, + { + "data": { + "text/html": [ + "
Model: \"sequential\"\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1mModel: \"sequential\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ mobilenet_1.00_224 (Functional) │ (None, 7, 7, 1024)     │     3,228,864 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d (MaxPooling2D)    │ (None, 3, 3, 1024)     │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten (Flatten)               │ (None, 9216)           │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (Dense)                   │ (None, 32)             │       294,944 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (Dropout)               │ (None, 32)             │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (Dense)                 │ (None, 5)              │           165 │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ mobilenet_1.00_224 (\u001b[38;5;33mFunctional\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m1024\u001b[0m) │ \u001b[38;5;34m3,228,864\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m1024\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m9216\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m294,944\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m) │ \u001b[38;5;34m165\u001b[0m │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 3,523,973 (13.44 MB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m3,523,973\u001b[0m (13.44 MB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 295,109 (1.13 MB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m295,109\u001b[0m (1.13 MB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 3,228,864 (12.32 MB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m3,228,864\u001b[0m (12.32 MB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "check_var_defined('model_mobilenet')\n", "model_mobilenet.summary()" @@ -2372,7 +3008,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 41, "id": "b06557e3", "metadata": { "deletable": false, @@ -2388,16 +3024,50 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 429ms/step - categorical_accuracy: 0.2296 - loss: 2.5558 - val_categorical_accuracy: 0.4741 - val_loss: 1.2791\n", + "Epoch 2/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 418ms/step - categorical_accuracy: 0.4566 - loss: 1.2256 - val_categorical_accuracy: 0.7193 - val_loss: 0.8473\n", + "Epoch 3/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 419ms/step - categorical_accuracy: 0.6146 - loss: 0.9444 - val_categorical_accuracy: 0.7956 - val_loss: 0.6352\n", + "Epoch 4/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m43s\u001b[0m 462ms/step - categorical_accuracy: 0.6761 - loss: 0.7756 - val_categorical_accuracy: 0.8501 - val_loss: 0.5471\n", + "Epoch 5/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 444ms/step - categorical_accuracy: 0.7207 - loss: 0.6936 - val_categorical_accuracy: 0.8365 - val_loss: 0.4774\n", + "Epoch 6/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 420ms/step - categorical_accuracy: 0.7470 - loss: 0.6032 - val_categorical_accuracy: 0.8638 - val_loss: 0.4606\n", + "Epoch 7/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 417ms/step - categorical_accuracy: 0.7697 - loss: 0.5277 - val_categorical_accuracy: 0.8665 - val_loss: 0.4382\n", + "Epoch 8/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 431ms/step - categorical_accuracy: 0.7939 - loss: 0.4792 - val_categorical_accuracy: 0.8828 - val_loss: 0.4102\n", + "Epoch 9/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 448ms/step - categorical_accuracy: 0.7955 - loss: 0.4710 - val_categorical_accuracy: 0.8747 - val_loss: 0.3781\n", + "Epoch 10/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 438ms/step - categorical_accuracy: 0.7994 - loss: 0.4482 - val_categorical_accuracy: 0.8747 - val_loss: 0.3842\n" + ] + } + ], "source": [ "tf.keras.utils.set_random_seed(9673)\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_mobilenet.compile(loss=\"categorical_crossentropy\",\n", + " optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n", + " metrics=[tf.keras.metrics.CategoricalAccuracy()])\n", + "\n", + "history_mobilenet = model_mobilenet.fit(x_train, y_train, epochs=10,\n", + " validation_data=(x_val, y_val),\n", + " batch_size=32)\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 42, "id": "6268f779", "metadata": { "deletable": false, @@ -2414,14 +3084,22 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "history_mobilenet defined.\n" + ] + } + ], "source": [ "check_var_defined('history_mobilenet')" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 43, "id": "6cbcc8b8", "metadata": { "deletable": false, @@ -2437,14 +3115,35 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plot_metrics(history_mobilenet)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 44, "id": "fd842596", "metadata": { "deletable": false, @@ -2460,7 +3159,26 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 414ms/step\n", + "Average Recall: 0.885, Average Precision 0.881\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "test_targets_mobilenet = model_predict(model_mobilenet, x_test)\n", "recall_mobilenet, precision_mobilenet = average_recall_precision(test_targets, test_targets_mobilenet) \n", @@ -2469,7 +3187,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 45, "id": "e2342a8b", "metadata": { "deletable": false, @@ -2486,7 +3204,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "test_targets_mobilenet defined.\n", + "recall_mobilenet defined.\n" + ] + } + ], "source": [ "check_var_defined('test_targets_mobilenet')\n", "check_var_defined('recall_mobilenet')\n" @@ -2494,7 +3221,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 46, "id": "2bb96e04", "metadata": { "deletable": false, @@ -2511,7 +3238,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "precision_mobilenet defined.\n" + ] + } + ], "source": [ "check_var_defined('precision_mobilenet')\n" ] @@ -2555,7 +3290,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The initial accuracy started lower and the loss higher than with the other models. However, the transfer model was able to learn much more quickly and overtook the other models within a few generations. The average precision and recall are significantly better, and it can be seen from the confusion matrix that there was a much lower proportion of misclassification, with the model being very good at positive classification." ] }, { @@ -2597,7 +3332,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "As always, more training data and more tranining time would improve the results. Learning reate scheduling to reduce the learning rate during training could allow for faster convergence of the model. Different optimisation functions from Adam could also improve results. A deeper model architecture could allow for more nuanced features to be learned." ] } ], diff --git a/cw2/spce0038_coursework_tf_MCMQ7.ipynb b/cw2/spce0038_coursework_tf_MCMQ7.ipynb index d101afd..f3c9312 100644 --- a/cw2/spce0038_coursework_tf_MCMQ7.ipynb +++ b/cw2/spce0038_coursework_tf_MCMQ7.ipynb @@ -67,7 +67,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "3593c649", "metadata": {}, "outputs": [], @@ -132,7 +132,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "id": "a32c7c90", "metadata": { "deletable": false, @@ -153,13 +153,13 @@ "name": "stderr", "output_type": "stream", "text": [ - "2025-03-14 14:07:37.610956: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2025-03-14 14:07:37.788469: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2025-03-14 14:07:37.950994: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", + "2025-03-20 22:24:16.798627: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", + "2025-03-20 22:24:16.801652: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", + "2025-03-20 22:24:16.811341: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n", - "E0000 00:00:1741961258.106221 71564 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", - "E0000 00:00:1741961258.153214 71564 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", - "2025-03-14 14:07:38.479758: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", + "E0000 00:00:1742509456.827236 468842 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", + "E0000 00:00:1742509456.832323 468842 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", + "2025-03-20 22:24:16.848642: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n" ] } @@ -174,7 +174,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 3, "id": "fad96611", "metadata": { "deletable": false, @@ -251,7 +251,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 4, "id": "f9c193a0", "metadata": { "deletable": false, @@ -272,38 +272,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "2025-03-14 14:44:13.164833: W external/local_tsl/tsl/platform/cloud/google_auth_provider.cc:184] All attempts to get a Google authentication bearer token failed, returning an empty token. Retrieving token from files failed with \"NOT_FOUND: Could not locate the credentials file.\". Retrieving token from GCE failed with \"FAILED_PRECONDITION: Error executing an HTTP request: libcurl code 6 meaning 'Couldn't resolve host name', error details: Could not resolve host: metadata.google.internal\".\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1mDownloading and preparing dataset 218.21 MiB (download: 218.21 MiB, generated: 221.83 MiB, total: 440.05 MiB) to /home/ktyl/tensorflow_datasets/tf_flowers/3.0.1...\u001b[0m\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/ktyl/.conda/envs/mlbd/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", - " from .autonotebook import tqdm as notebook_tqdm\n", - "Dl Completed...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:31<00:00, 6.22s/ file]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1mDataset tf_flowers downloaded and prepared to /home/ktyl/tensorflow_datasets/tf_flowers/3.0.1. Subsequent calls will reuse this data.\u001b[0m\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "W0000 00:00:1741963485.913699 71564 gpu_device.cc:2344] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n", + "W0000 00:00:1742509459.195582 468842 gpu_device.cc:2344] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n", "Skipping registering GPU devices...\n" ] } @@ -315,7 +284,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "id": "e438b1ef", "metadata": { "deletable": false, @@ -336,8 +305,8 @@ "name": "stderr", "output_type": "stream", "text": [ - "2025-03-14 14:44:46.016395: I tensorflow/core/kernels/data/tf_record_dataset_op.cc:376] The default buffer size is 262144, which is overridden by the user specified `buffer_size` of 8388608\n", - "2025-03-14 14:44:46.984183: I tensorflow/core/framework/local_rendezvous.cc:405] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence\n" + "2025-03-20 22:24:19.295704: I tensorflow/core/kernels/data/tf_record_dataset_op.cc:376] The default buffer size is 262144, which is overridden by the user specified `buffer_size` of 8388608\n", + "2025-03-20 22:24:20.423168: I tensorflow/core/framework/local_rendezvous.cc:405] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence\n" ] } ], @@ -369,7 +338,7 @@ }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 6, "id": "69bf403d", "metadata": { "deletable": false, @@ -475,7 +444,7 @@ }, { "cell_type": "code", - "execution_count": 64, + "execution_count": 7, "id": "2f2da49d", "metadata": { "deletable": false, @@ -520,7 +489,7 @@ }, { "cell_type": "code", - "execution_count": 65, + "execution_count": 8, "id": "5b886c27", "metadata": { "deletable": false, @@ -573,7 +542,7 @@ }, { "cell_type": "code", - "execution_count": 67, + "execution_count": 9, "id": "a880cd0d", "metadata": { "deletable": false, @@ -597,7 +566,7 @@ }, { "cell_type": "code", - "execution_count": 68, + "execution_count": 10, "id": "f767e9cf", "metadata": { "deletable": false, @@ -653,7 +622,7 @@ }, { "cell_type": "code", - "execution_count": 74, + "execution_count": 11, "id": "e40efe42", "metadata": { "deletable": false, @@ -711,7 +680,7 @@ }, { "cell_type": "code", - "execution_count": 77, + "execution_count": 12, "id": "b91925ad", "metadata": { "deletable": false, @@ -735,7 +704,7 @@ }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 13, "id": "008bf36d", "metadata": { "deletable": false, @@ -839,7 +808,7 @@ }, { "cell_type": "code", - "execution_count": 86, + "execution_count": 14, "id": "5fb75b70", "metadata": { "deletable": false, @@ -876,7 +845,7 @@ }, { "cell_type": "code", - "execution_count": 87, + "execution_count": 15, "id": "caaff270", "metadata": { "deletable": false, @@ -941,7 +910,7 @@ }, { "cell_type": "code", - "execution_count": 88, + "execution_count": 16, "id": "156ef4a4", "metadata": { "deletable": false, @@ -1029,7 +998,13 @@ } }, "source": [ - "YOUR ANSWER HERE" + "A common problem with activation functions is that of vanishing gradients in lower layers, when gradients become very small and cease to be updated in training, or exploding gradients, in which case the training algorithm may not converge. We use different activation functions to avoid this problem. The choice of activation function depends on multiple factors, one of which is whether the data has negative values or not. In our case, it does not - we normalised the data into the range (0, 1)\n", + "\n", + "The convolutional layer should use a ReLU activation function to prevent vanishing gradients, as the function's gradient is never zero for positive values.\n", + "\n", + "The dense layer should also use ReLU, for the same reason as the convolutional layer. It could use Tanh if negative values were present.\n", + "\n", + "The activation function for the output layer depends on the problem type. In our case we are doing multi-class classification, so we should use Softmax to map predictions to probabilities The probabilities for each class will sum to 1." ] }, { @@ -1074,7 +1049,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "id": "b869ea33", "metadata": { "deletable": false, @@ -1090,18 +1065,41 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/ktyl/.conda/envs/mlbd/lib/python3.11/site-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", + " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" + ] + } + ], "source": [ "tf.keras.backend.clear_session()\n", "tf.keras.utils.set_random_seed(93612)\n", "\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_basic = tf.keras.models.Sequential([\n", + " tf.keras.layers.Conv2D(filters=8, kernel_size=(3,3), activation=\"relu\", input_shape=(224,224,3)),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=16, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Flatten(),\n", + " tf.keras.layers.Dense(32, activation=\"relu\"),\n", + " tf.keras.layers.Dense(5, activation=\"softmax\")\n", + "])\n", + "\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "id": "dfd1b4b1", "metadata": { "deletable": false, @@ -1118,7 +1116,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('model_basic')" ] @@ -1166,7 +1172,9 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Categorical Cross-Entropy (CCE) is an appropriate loss function because we are using one-hot encoding and the softmax looss function. One-hot encoding works well with the softmax activation function as we are comparing probabilities and one-hot produces a multi-dimensional vector.\n", + "\n", + "We can measure categorial accuracy as a metric since the dataset is one-hot encodded and relatively balanced. The metric measures the proportion of predictions matching one-hot labels." ] }, { @@ -1192,7 +1200,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "id": "0daef6f2", "metadata": { "deletable": false, @@ -1211,12 +1219,15 @@ "outputs": [], "source": [ "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_basic.compile(loss=\"categorical_crossentropy\",\n", + " optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n", + " metrics=[tf.keras.metrics.CategoricalAccuracy()])\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "id": "b3f30c12", "metadata": { "deletable": false, @@ -1233,7 +1244,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('model_basic')" ] @@ -1261,7 +1280,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "id": "5f355c96", "metadata": { "deletable": false, @@ -1277,16 +1296,46 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 216ms/step - categorical_accuracy: 0.3034 - loss: 1.5835 - val_categorical_accuracy: 0.3842 - val_loss: 1.4783\n", + "Epoch 2/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 201ms/step - categorical_accuracy: 0.4216 - loss: 1.3884 - val_categorical_accuracy: 0.4741 - val_loss: 1.3093\n", + "Epoch 3/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 199ms/step - categorical_accuracy: 0.4820 - loss: 1.2396 - val_categorical_accuracy: 0.4932 - val_loss: 1.2155\n", + "Epoch 4/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 199ms/step - categorical_accuracy: 0.5169 - loss: 1.1568 - val_categorical_accuracy: 0.4932 - val_loss: 1.1751\n", + "Epoch 5/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 198ms/step - categorical_accuracy: 0.5300 - loss: 1.1089 - val_categorical_accuracy: 0.5177 - val_loss: 1.1498\n", + "Epoch 6/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 198ms/step - categorical_accuracy: 0.5450 - loss: 1.0736 - val_categorical_accuracy: 0.5259 - val_loss: 1.1298\n", + "Epoch 7/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 199ms/step - categorical_accuracy: 0.5634 - loss: 1.0433 - val_categorical_accuracy: 0.5368 - val_loss: 1.1149\n", + "Epoch 8/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 206ms/step - categorical_accuracy: 0.5852 - loss: 1.0178 - val_categorical_accuracy: 0.5450 - val_loss: 1.0949\n", + "Epoch 9/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 206ms/step - categorical_accuracy: 0.5967 - loss: 0.9953 - val_categorical_accuracy: 0.5559 - val_loss: 1.0862\n", + "Epoch 10/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 199ms/step - categorical_accuracy: 0.6108 - loss: 0.9734 - val_categorical_accuracy: 0.5613 - val_loss: 1.0745\n" + ] + } + ], "source": [ "tf.keras.utils.set_random_seed(47290)\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "history_basic = model_basic.fit(x_train, y_train, epochs=10,\n", + " validation_data=(x_val, y_val),\n", + " batch_size=32)\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "id": "d123574b", "metadata": { "deletable": false, @@ -1303,7 +1352,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "history_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('history_basic')" ] @@ -1331,7 +1388,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "id": "38bb58e0", "metadata": { "deletable": false, @@ -1347,11 +1404,48 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAHHCAYAAABDUnkqAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAby1JREFUeJzt3Xd00/X+x/Fnmu5JaUsHlJa9KXtPAQERWQoiyrpuQBH1Cj8njotbruJ13Ss4GC5AVJClyJa9N3Qw2jK7d5PfH4FAGR3QNm36epyTc5PvSN6hXvriMw1ms9mMiIiIiJ1wsHUBIiIiIsVJ4UZERETsisKNiIiI2BWFGxEREbErCjciIiJiVxRuRERExK4o3IiIiIhdUbgRERERu6JwIyIiInZF4UbEhkaPHk14ePhN3fvKK69gMBiKt6AKZNWqVRgMBlatWmU9VtifR1RUFAaDgVmzZhVrTeHh4YwePbpY31OkIlK4EbkOg8FQqMeVvxil5DRt2pTq1auT324xHTt2JDAwkJycnFKsrOjWr1/PK6+8QkJCgq1LsZo1axYGg4EtW7bYuhSRYuFo6wJEyqJvvvkmz+uvv/6a5cuXX3O8QYMGt/Q5X3zxBSaT6abufeGFF5g8efItfX55MWLECCZPnsyaNWvo0qXLNeejoqLYsGED48ePx9Hx5v9au5WfR2GtX7+eqVOnMnr0aCpVqpTn3MGDB3Fw0L85RW6Vwo3Iddx///15Xm/cuJHly5dfc/xqaWlpuLu7F/pznJycbqo+AEdHx1v6RV6e3HfffUyZMoU5c+ZcN9zMnTsXs9nMiBEjbulzbuXnURxcXFxs+vki9kL/RBC5Sd26daNx48Zs3bqVLl264O7uzv/93/8B8PPPP9OvXz9CQkJwcXGhVq1avPbaa+Tm5uZ5j6vHeFway/Huu+/y+eefU6tWLVxcXGjdujWbN2/Oc+/1xtwYDAbGjx/PwoULady4MS4uLjRq1Ijff//9mvpXrVpFq1atcHV1pVatWnz22WeFGsczfvx4PD09SUtLu+bc8OHDCQoKsn7PLVu20Lt3b/z9/XFzc6NGjRqMHTs23/e/ntDQULp06cKPP/5Idnb2NefnzJlDrVq1aNu2LdHR0Tz++OPUq1cPNzc3/Pz8uOeee4iKiirwc6435iYhIYHRo0fj4+NDpUqVGDVq1HW7lHbt2sXo0aOpWbMmrq6uBAUFMXbsWM6dO2e95pVXXuHZZ58FoEaNGtbuzUu1XW/MzbFjx7jnnnuoXLky7u7utGvXjt9++y3PNZfGD33//fe88cYbVKtWDVdXV3r06MGRI0cK/N6FtX37dvr27Yu3tzeenp706NGDjRs35rkmOzubqVOnUqdOHVxdXfHz86NTp04sX77cek1cXBxjxoyhWrVquLi4EBwczIABAwr1MxIpjIrxzz6REnLu3Dn69u3Lvffey/33309gYCBgGcPg6enJpEmT8PT05I8//uCll14iKSmJd955p8D3nTNnDsnJyTzyyCMYDAbefvttBg8ezLFjxwpsXVi7di3z58/n8ccfx8vLiw8//JAhQ4YQExODn58fYPkl1adPH4KDg5k6dSq5ubm8+uqrBAQEFFjbsGHD+Pjjj/ntt9+45557rMfT0tL45ZdfGD16NEajkdOnT3P77bcTEBDA5MmTqVSpElFRUcyfP7/Az7ieESNG8PDDD7N06VLuvPNO6/Hdu3ezZ88eXnrpJQA2b97M+vXruffee6lWrRpRUVF88skndOvWjX379hWpZc1sNjNgwADWrl3Lo48+SoMGDViwYAGjRo265trly5dz7NgxxowZQ1BQEHv37uXzzz9n7969bNy4EYPBwODBgzl06BBz587lgw8+wN/fH+CGf+7x8fF06NCBtLQ0nnjiCfz8/Pjqq6+46667+PHHHxk0aFCe6998800cHBx45plnSExM5O2332bEiBH8/fffhf7ON7J37146d+6Mt7c3//znP3FycuKzzz6jW7du/PXXX7Rt2xawBLhp06bx4IMP0qZNG5KSktiyZQvbtm2jV69eAAwZMoS9e/cyYcIEwsPDOX36NMuXLycmJuamB9iL5GEWkQKNGzfOfPX/Xbp27WoGzJ9++uk116elpV1z7JFHHjG7u7ubMzIyrMdGjRplDgsLs76OjIw0A2Y/Pz/z+fPnrcd//vlnM2D+5ZdfrMdefvnla2oCzM7OzuYjR45Yj+3cudMMmD/66CPrsf79+5vd3d3NJ0+etB47fPiw2dHR8Zr3vJrJZDJXrVrVPGTIkDzHv//+ezNgXr16tdlsNpsXLFhgBsybN2/O9/0K6/z582YXFxfz8OHD8xyfPHmyGTAfPHjQbDZf/89+w4YNZsD89ddfW4/9+eefZsD8559/Wo9d/fNYuHChGTC//fbb1mM5OTnmzp07mwHzzJkzrcev97lz587N82diNpvN77zzjhkwR0ZGXnN9WFiYedSoUdbXEydONAPmNWvWWI8lJyeba9SoYQ4PDzfn5ubm+S4NGjQwZ2ZmWq/997//bQbMu3fvvuazrjRz5swCf1YDBw40Ozs7m48ePWo9durUKbOXl5e5S5cu1mMRERHmfv363fB9Lly4YAbM77zzTr41idwKdUuJ3AIXFxfGjBlzzXE3Nzfr8+TkZM6ePUvnzp1JS0vjwIEDBb7vsGHD8PX1tb7u3LkzYOmiKEjPnj2pVauW9XXTpk3x9va23pubm8uKFSsYOHAgISEh1utq165N3759C3x/g8HAPffcw+LFi0lJSbEe/+6776hatSqdOnUCsA6W/fXXX6/blVRUvr6+3HHHHSxatIjU1FTA0rIyb948WrVqRd26dYG8f/bZ2dmcO3eO2rVrU6lSJbZt21akz1y8eDGOjo489thj1mNGo5EJEyZcc+2Vn5uRkcHZs2dp164dQJE/98rPb9OmjfXPFMDT05OHH36YqKgo9u3bl+f6MWPG4OzsbH1dlP9u8pObm8uyZcsYOHAgNWvWtB4PDg7mvvvuY+3atSQlJQGWn/vevXs5fPjwdd/Lzc0NZ2dnVq1axYULF26pLpEbUbgRuQVVq1bN88vkkr179zJo0CB8fHzw9vYmICDAOhg5MTGxwPetXr16nteXgk5hfhlcfe+l+y/de/r0adLT06ldu/Y1113v2PUMGzaM9PR0Fi1aBEBKSgqLFy/mnnvusY7Z6dq1K0OGDGHq1Kn4+/szYMAAZs6cSWZmZqE+43pGjBhBamoqP//8M2CZeRQVFZVnIHF6ejovvfQSoaGhuLi44O/vT0BAAAkJCYX6s79SdHQ0wcHBeHp65jler169a649f/48Tz75JIGBgbi5uREQEECNGjWAwv3Mb/T51/usS7P0oqOj8xy/lf9u8nPmzBnS0tJuWIvJZOL48eMAvPrqqyQkJFC3bl2aNGnCs88+y65du6zXu7i48NZbb7FkyRICAwPp0qULb7/9NnFxcbdUo8iVFG5EbsGV/1q/JCEhga5du7Jz505effVVfvnlF5YvX85bb70FUKipxkaj8brHzfms81Ic9xZWu3btCA8P5/vvvwfgl19+IT09nWHDhlmvMRgM/Pjjj9Yp2idPnmTs2LG0bNkyT4tPUdx55534+PgwZ84cwDI2yWg0cu+991qvmTBhAm+88QZDhw7l+++/Z9myZSxfvhw/P78SneY9dOhQvvjiCx599FHmz5/PsmXLrAO5S3p6+SWl8bMvSJcuXTh69ChffvkljRs35r///S8tWrTgv//9r/WaiRMncujQIaZNm4arqysvvvgiDRo0YPv27aVWp9g3hRuRYrZq1SrOnTvHrFmzePLJJ7nzzjvp2bNnnm4mW6pSpQqurq7XnUVTlJk1Q4cO5ffffycpKYnvvvuO8PBwazfMldq1a8cbb7zBli1bmD17Nnv37mXevHk3VbuLiwt33303y5YtIz4+nh9++IHbbruNoKAg6zU//vgjo0aN4r333uPuu++mV69edOrU6aYWzQsLCyM2NvaaMHbw4ME8ry9cuMDKlSuZPHkyU6dOZdCgQfTq1StPF84lRVlVOiws7JrPAqxdm2FhYYV+r1sREBCAu7v7DWtxcHAgNDTUeqxy5cqMGTOGuXPncvz4cZo2bcorr7yS575atWrx9NNPs2zZMvbs2UNWVhbvvfdeSX8VqSAUbkSK2aV/PV/5r+WsrCz+85//2KqkPIxGIz179mThwoWcOnXKevzIkSMsWbKk0O8zbNgwMjMz+eqrr/j9998ZOnRonvMXLly4psWgWbNmAHm6po4ePcrRo0cL/bkjRowgOzubRx55hDNnzlyzto3RaLzmcz/66KNrpuEXxh133EFOTg6ffPKJ9Vhubi4fffTRNZ8J17aQTJ8+/Zr39PDwAChU2LrjjjvYtGkTGzZssB5LTU3l888/Jzw8nIYNGxb2q9wSo9HI7bffzs8//5xnunZ8fDxz5syhU6dOeHt7A+SZ+g6WMUK1a9e2/szT0tLIyMjIc02tWrXw8vK6pS5LkStpKrhIMevQoQO+vr6MGjWKJ554AoPBwDfffFOqXQMFeeWVV1i2bBkdO3bkscceIzc3lxkzZtC4cWN27NhRqPdo0aIFtWvX5vnnnyczMzNPlxTAV199xX/+8x8GDRpErVq1SE5O5osvvsDb25s77rjDel2PHj0ACr3GSdeuXalWrRo///wzbm5uDB48OM/5O++8k2+++QYfHx8aNmzIhg0bWLFihXUafFH079+fjh07MnnyZKKiomjYsCHz58+/ZgyNt7e3dexIdnY2VatWZdmyZURGRl7zni1btgTg+eef595778XJyYn+/ftbQ8+VJk+ezNy5c+nbty9PPPEElStX5quvviIyMpKffvqp2Fcz/vLLL6+7JtKTTz7J66+/zvLly+nUqROPP/44jo6OfPbZZ2RmZvL2229br23YsCHdunWjZcuWVK5cmS1btvDjjz8yfvx4AA4dOkSPHj0YOnQoDRs2xNHRkQULFhAfH5+ne1HkVijciBQzPz8/fv31V55++mleeOEFfH19uf/+++nRowe9e/e2dXmA5RfskiVLeOaZZ3jxxRcJDQ3l1VdfZf/+/YWazXXJsGHDeOONN6hduzYtWrTIc65r165s2rSJefPmER8fj4+PD23atGH27NnWgbY3w8HBgeHDh/POO+/Qv39/vLy88pz/97//jdFoZPbs2WRkZNCxY0dWrFhxU3/2Dg4OLFq0iIkTJ/Ltt99iMBi46667eO+992jevHmea+fMmcOECRP4+OOPMZvN3H777SxZsiTPjDSA1q1b89prr/Hpp5/y+++/YzKZiIyMvG64CQwMZP369Tz33HN89NFHZGRk0LRpU3755Rf69etX5O9TkCtbqK40evRoGjVqxJo1a5gyZQrTpk3DZDLRtm1bvv32W+saNwBPPPEEixYtYtmyZWRmZhIWFsbrr79uXbwwNDSU4cOHs3LlSr755hscHR2pX78+33//PUOGDCn27yQVk8Fclv45KSI2NXDgwHyn8YqIlAcacyNSQaWnp+d5ffjwYRYvXky3bt1sU5CISDFRy41IBRUcHGzdCyk6OppPPvmEzMxMtm/fTp06dWxdnojITdOYG5EKqk+fPsydO5e4uDhcXFxo3749//rXvxRsRKTcU8uNiIiI2BWNuRERERG7onAjIiIidqXCjbkxmUycOnUKLy+vIi2DLiIiIrZjNptJTk4mJCSkwAUsK1y4OXXqVJ49UERERKT8OH78ONWqVcv3mgoXbi6tZnr8+HHrXigiIiJStiUlJREaGnrNquTXU+HCzaWuKG9vb4UbERGRcqYwQ0o0oFhERETsisKNiIiI2BWFGxEREbErFW7MjYiI3Lrc3Fyys7NtXYbYGWdn5wKneReGwo2IiBSa2WwmLi6OhIQEW5cidsjBwYEaNWrg7Ox8S++jcCMiIoV2KdhUqVIFd3d3LYYqxebSIruxsbFUr179lv7bUrgREZFCyc3NtQYbPz8/W5cjdiggIIBTp06Rk5ODk5PTTb+PBhSLiEihXBpj4+7ubuNKxF5d6o7Kzc29pfdRuBERkSJRV5SUlOL6b0vhRkREROyKwo2IiEgRhYeHM3369EJfv2rVKgwGg2aZlRKFGxERsVsGgyHfxyuvvHJT77t582YefvjhQl/foUMHYmNj8fHxuanPKyyFKAvNlipGiWnZRJ5LpVloJVuXIiIiQGxsrPX5d999x0svvcTBgwetxzw9Pa3PzWYzubm5ODoW/KsxICCgSHU4OzsTFBRUpHvk5qnlpphsi7lAu2kreezbrWTnmmxdjoiIAEFBQdaHj48PBoPB+vrAgQN4eXmxZMkSWrZsiYuLC2vXruXo0aMMGDCAwMBAPD09ad26NStWrMjzvld3SxkMBv773/8yaNAg3N3dqVOnDosWLbKev7pFZdasWVSqVImlS5fSoEEDPD096dOnT54wlpOTwxNPPEGlSpXw8/PjueeeY9SoUQwcOPCm/zwuXLjAyJEj8fX1xd3dnb59+3L48GHr+ejoaPr374+vry8eHh40atSIxYsXW+8dMWIEAQEBuLm5UadOHWbOnHnTtZQkhZti0jDYG3dnI7GJGSzdG2frckRESoXZbCYtK6fUH2azudi+w+TJk3nzzTfZv38/TZs2JSUlhTvuuIOVK1eyfft2+vTpQ//+/YmJicn3faZOncrQoUPZtWsXd9xxByNGjOD8+fM3vD4tLY13332Xb775htWrVxMTE8MzzzxjPf/WW28xe/ZsZs6cybp160hKSmLhwoW39F1Hjx7Nli1bWLRoERs2bMBsNnPHHXdYp/mPGzeOzMxMVq9eze7du3nrrbesrVsvvvgi+/btY8mSJezfv59PPvkEf3//W6qnpKhbqpi4OhkZ0S6MD1ceZua6KO5sGmLrkkRESlx6di4NX1pa6p+779XeuDsXz6+wV199lV69ellfV65cmYiICOvr1157jQULFrBo0SLGjx9/w/cZPXo0w4cPB+Bf//oXH374IZs2baJPnz7XvT47O5tPP/2UWrVqATB+/HheffVV6/mPPvqIKVOmMGjQIABmzJhhbUW5GYcPH2bRokWsW7eODh06ADB79mxCQ0NZuHAh99xzDzExMQwZMoQmTZoAULNmTev9MTExNG/enFatWgGW1quySi03xej+dtVxMhrYGn2BnccTbF2OiIgUwqVf1pekpKTwzDPP0KBBAypVqoSnpyf79+8vsOWmadOm1uceHh54e3tz+vTpG17v7u5uDTYAwcHB1usTExOJj4+nTZs21vNGo5GWLVsW6btdaf/+/Tg6OtK2bVvrMT8/P+rVq8f+/fsBeOKJJ3j99dfp2LEjL7/8Mrt27bJe+9hjjzFv3jyaNWvGP//5T9avX3/TtZQ0tdwUoypertzZNIQF208yc10k0+9tbuuSRERKlJuTkX2v9rbJ5xYXDw+PPK+feeYZli9fzrvvvkvt2rVxc3Pj7rvvJisrK9/3uXq7AIPBgMl04zGY17u+OLvbbsaDDz5I7969+e2331i2bBnTpk3jvffeY8KECfTt25fo6GgWL17M8uXL6dGjB+PGjePdd9+1ac3Xo5abYjamYzgAv+2O5XRShm2LEREpYQaDAXdnx1J/lOQqyevWrWP06NEMGjSIJk2aEBQURFRUVIl93vX4+PgQGBjI5s2brcdyc3PZtm3bTb9ngwYNyMnJ4e+//7YeO3fuHAcPHqRhw4bWY6GhoTz66KPMnz+fp59+mi+++MJ6LiAggFGjRvHtt98yffp0Pv/885uupySp5aaYNa1WiVZhvmyJvsC3G6OZdHs9W5ckIiJFUKdOHebPn0///v0xGAy8+OKL+bbAlJQJEyYwbdo0ateuTf369fnoo4+4cOFCoYLd7t278fLysr42GAxEREQwYMAAHnroIT777DO8vLyYPHkyVatWZcCAAQBMnDiRvn37UrduXS5cuMCff/5JgwYNAHjppZdo2bIljRo1IjMzk19//dV6rqxRuCkBYzrWYEv0BWb/HcPj3WvjWozNpyIiUrLef/99xo4dS4cOHfD39+e5554jKSmp1Ot47rnniIuLY+TIkRiNRh5++GF69+6N0Vjw75QuXbrkeW00GsnJyWHmzJk8+eST3HnnnWRlZdGlSxcWL15s7SLLzc1l3LhxnDhxAm9vb/r06cMHH3wAWNbqmTJlClFRUbi5udG5c2fmzZtX/F+8GBjMtu7gK2VJSUn4+PiQmJiIt7d3iXxGTq6JLm//yanEDN6+uylDW4WWyOeIiJSmjIwMIiMjqVGjBq6urrYup8IxmUw0aNCAoUOH8tprr9m6nBKR339jRfn9rTE3JcDR6MAD7cMBmLkuyuYDxEREpPyJjo7miy++4NChQ+zevZvHHnuMyMhI7rvvPluXVuYp3JSQ4W1CcXVyYH9sEn9H3ngRJxERketxcHBg1qxZtG7dmo4dO7J7925WrFhRZse5lCUac1NCKrk7M7hFNeb8HcPMdZG0q+ln65JERKQcCQ0NZd26dbYuo1xSy00JGtMhHIBl++I5fj7NtsWIiIhUEAo3JahOoBed6/hjNsNX66NsXY6IiEiFoHBTwsZ2rAHAd1uOk5qZY+NqRERE7J/CTQnrWjeAmv4eJGfk8NO2E7YuR0RExO4p3JQwBwcDoy6OvZm5LgqTSdPCRURESpLCTSm4u2U1vFwdiTybyl+Hzti6HBEREbumcFMKPFwcGXZxleIv10XauBoRESmqbt26MXHiROvr8PBwpk+fnu89BoOBhQsX3vJnF9f7VCQKN6VkVIdwHAyw5vBZDscn27ocEZEKoX///vTp0+e659asWYPBYGDXrl1Fft/Nmzfz8MMP32p5ebzyyis0a9bsmuOxsbH07du3WD/rarNmzaJSpUol+hmlyabhZvXq1fTv35+QkJBCJdNVq1ZhMBiuecTFxZVOwbcgtLI7PRsEAjBT08JFRErFP/7xD5YvX86JE9dO6Jg5cyatWrWiadOmRX7fgIAA3N3di6PEAgUFBeHi4lIqn2UvbBpuUlNTiYiI4OOPPy7SfQcPHiQ2Ntb6qFKlSglVWLzGdrJMC5+/7QQJaVk2rkZExP7deeedBAQEMGvWrDzHU1JS+OGHH/jHP/7BuXPnGD58OFWrVsXd3Z0mTZowd+7cfN/36m6pw4cP06VLF1xdXWnYsCHLly+/5p7nnnuOunXr4u7uTs2aNXnxxRfJzs4GLC0nU6dOZefOndZ/uF+q+ep//O/evZvbbrsNNzc3/Pz8ePjhh0lJSbGeHz16NAMHDuTdd98lODgYPz8/xo0bZ/2smxETE8OAAQPw9PTE29uboUOHEh8fbz2/c+dOunfvjpeXF97e3rRs2ZItW7YAlj2y+vfvj6+vLx4eHjRq1IjFixffdC2FYdPtF/r27XtTTW1VqlQpl81nbWtUpkGwN/tjk5i3+TiPdq1l65JERG6N2QzZNliB3ckdDIYCL3N0dGTkyJHMmjWL559/HsPFe3744Qdyc3MZPnw4KSkptGzZkueeew5vb29+++03HnjgAWrVqkWbNm0K/AyTycTgwYMJDAzk77//JjExMc/4nEu8vLyYNWsWISEh7N69m4ceeggvLy/++c9/MmzYMPbs2cPvv//OihUrAPDx8bnmPVJTU+nduzft27dn8+bNnD59mgcffJDx48fnCXB//vknwcHB/Pnnnxw5coRhw4bRrFkzHnrooQK/z/W+36Vg89dff5GTk8O4ceMYNmwYq1atAmDEiBE0b96cTz75BKPRyI4dO3BycgJg3LhxZGVlsXr1ajw8PNi3bx+enp5FrqMoyuXeUs2aNSMzM5PGjRvzyiuv0LFjR1uXVCgGg4ExHcP554+7+Hp9FA92qoGjUcOeRKQcy06Df4WU/uf+3ylw9ijUpWPHjuWdd97hr7/+olu3boClS2rIkCH4+Pjg4+PDM888Y71+woQJLF26lO+//75Q4WbFihUcOHCApUuXEhJi+bP417/+dc0/3l944QXr8/DwcJ555hnmzZvHP//5T9zc3PD09MTR0ZGgoKAbftacOXPIyMjg66+/xsPD8v1nzJhB//79eeuttwgMtAx/8PX1ZcaMGRiNRurXr0+/fv1YuXLlTYWblStXsnv3biIjIwkNtUyO+frrr2nUqBGbN2+mdevWxMTE8Oyzz1K/fn0A6tSpY70/JiaGIUOG0KRJEwBq1qxZ5BqKqlz9Zg0ODubTTz/lp59+4qeffiI0NJRu3bqxbdu2G96TmZlJUlJSnoct3RURgp+HM6cSM1i6N77gG0RE5JbUr1+fDh068OWXXwJw5MgR1qxZwz/+8Q8AcnNzee2112jSpAmVK1fG09OTpUuXEhMTU6j3379/P6GhodZgA9C+fftrrvvuu+/o2LEjQUFBeHp68sILLxT6M678rIiICGuwAejYsSMmk4mDBw9ajzVq1Aij0Wh9HRwczOnTp4v0WVd+ZmhoqDXYADRs2JBKlSqxf/9+ACZNmsSDDz5Iz549efPNNzl69Kj12ieeeILXX3+djh078vLLL9/UAO6iKlctN/Xq1aNevXrW1x06dODo0aN88MEHfPPNN9e9Z9q0aUydOrW0SiyQq5OREW2r8+EfR5i5LpJ+TYNtXZKIyM1zcre0otjic4vgH//4BxMmTODjjz9m5syZ1KpVi65duwLwzjvv8O9//5vp06fTpEkTPDw8mDhxIllZxTc2csOGDYwYMYKpU6fSu3dvfHx8mDdvHu+9916xfcaVLnUJXWIwGDCZTCXyWWCZ6XXffffx22+/sWTJEl5++WXmzZvHoEGDePDBB+nduze//fYby5YtY9q0abz33ntMmDChxOopVy0319OmTRuOHDlyw/NTpkwhMTHR+jh+/HgpVnd997cLw8loYEv0BXafSLR1OSIiN89gsHQPlfajEONtrjR06FAcHByYM2cOX3/9NWPHjrWOv1m3bh0DBgzg/vvvJyIigpo1a3Lo0KFCv3eDBg04fvw4sbGx1mMbN27Mc8369esJCwvj+eefp1WrVtSpU4fo6Og81zg7O5Obm1vgZ+3cuZPU1FTrsXXr1uHg4JDnH//F6dL3u/L35759+0hISKBhw4bWY3Xr1uWpp55i2bJlDB48mJkzZ1rPhYaG8uijjzJ//nyefvppvvjiixKp9ZJyH2527NhBcPCNWz9cXFzw9vbO87C1Kt6u9GtiqXmmFvUTESlxnp6eDBs2jClTphAbG8vo0aOt5+rUqcPy5ctZv349+/fv55FHHskzE6ggPXv2pG7duowaNYqdO3eyZs0ann/++TzX1KlTh5iYGObNm8fRo0f58MMPWbBgQZ5rwsPDiYyMZMeOHZw9e5bMzMxrPmvEiBG4uroyatQo9uzZw59//smECRN44IEHrONtblZubi47duzI89i/fz89e/akSZMmjBgxgm3btrFp0yZGjhxJ165dadWqFenp6YwfP55Vq1YRHR3NunXr2Lx5Mw0aNABg4sSJLF26lMjISLZt28aff/5pPVdSbBpuUlJSrH+AgPWHeqkPcsqUKYwcOdJ6/fTp0/n55585cuQIe/bsYeLEifzxxx+MGzfOFuXfkjEXdwv/ZdcpTidl2LgaERH7949//IMLFy7Qu3fvPONjXnjhBVq0aEHv3r3p1q0bQUFBDBw4sNDv6+DgwIIFC0hPT6dNmzY8+OCDvPHGG3muueuuu3jqqacYP348zZo1Y/369bz44ot5rhkyZAh9+vShe/fuBAQEXHc6uru7O0uXLuX8+fO0bt2au+++mx49ejBjxoyi/WFcR0pKCs2bN8/z6N+/PwaDgZ9//hlfX1+6dOlCz549qVmzJt999x0ARqORc+fOMXLkSOrWrcvQoUPp27evdUhIbm4u48aNo0GDBvTp04e6devyn//855brzY/BbDbbbCfHVatW0b1792uOjxo1ilmzZjF69GiioqKsU83efvttPv/8c06ePIm7uztNmzblpZdeuu573EhSUhI+Pj4kJibavBVnyCfr2Rp9gSd61GFSr7o2rUVEpCAZGRlERkZSo0YNXF1dbV2O2KH8/hsryu9vm4YbWyhL4ebXXacYP2c7/p7OrH3uNlydjAXfJCJiIwo3UtKKK9yU+zE35VnvRkEE+7hyNiWLX3baYLaBiIiIHVK4sSEnowMPtA8DYOa6KCpYI5qIiEiJULixseGtq+Pq5MC+2CQ2RZ63dTkiIiLlnsKNjfl6ODOoeTXA0nojIlLWqZVZSkpx/belcFMGjOkYDsCyfXEcP2+DDehERArh0qq3aWn6e0pKxqVVoa/cOuJmlKvtF8q03BzY/T0kx0Lnp4t0a91ALzrV9mftkbN8vSGK5/s1LPgmEZFSZjQaqVSpknWPInd3d+sqvyK3ymQycebMGdzd3XF0vLV4onBTXE5sgoWPgdEZIoaDd9F2yR3bKZy1R84yb/NxJvasi4eLfjQiUvZc2rH6ZjdhFMmPg4MD1atXv+XQrN+gxaV6e6jeAWLWw7p/Q9+3inR7t7pVqOHvQeTZVOZvO8ED7cNLpk4RkVtgMBgIDg6mSpUqZGdn27ocsTPOzs44ONz6iBmFm+JiMEC35+DrAbB1FnR6CryCCn27g4OBUe3DeOWXfcxcF8WItmE4OKi5V0TKJqPReMvjIkRKigYUF6caXSG0LeRkwLoPi3z73a1C8XJx5NjZVP46fKYEChQREbF/CjfFyWCArv+0PN/yJaQUrU/a08WRoa1DAU0LFxERuVkKN8WtVg+o2hJy0mH9R0W+fVT7cAwGWH3oDEdOJ5dAgSIiIvZN4aa4GQzQdbLl+eb/QurZIt1e3c+dng0CAbXeiIiI3AyFm5JQpxcEN4PsNNgwo8i3j+1YA4D5206SmKbZCCIiIkWhcFMSDAbo+pzl+aYvIK1oe0a1q1mZ+kFepGfnMm9zTAkUKCIiYr8UbkpKvb4Q1ASyUmDjf4p0q8FgsLbefL0hmpxcU0lUKCIiYpcUbkrKla03f38G6ReKdPtdzUKo7OHMyYR0lu2LL4ECRURE7JPCTUmq1w+qNILMJNj4aZFudXUyMqJtdQBmrossiepERETsksJNSXJwgK7PWp5v/AQyEot0+/3twnB0MLA56gJ7ThbtXhERkYpK4aakNRgAAfUhMxH+/rxItwZ6u9KvaTAAX6r1RkREpFAUbkqagwN0udh6s2EGZCQV6fYxFwcW/7LzFKeTM4q7OhEREbujcFMaGg0CvzqQkQCbvyjSrc1CK9GieiWyc83M3qhp4SIiIgVRuCkNDsbLrTfrZ0BmSpFuv9R6M/vvaDJzcou7OhEREbuicFNaGg+ByrUg/Txs+V+Rbu3TOIggb1fOpmTx687YEipQRETEPijclBajI3R5xvJ83YeQlVroW52MDjzQPgywDCw2m80lUaGIiIhdULgpTU3uAd9wSDsLW2YW6db72lTHxdGBvaeS2BxVtAUBRUREKhKFm9JkdILOT1uer/s3ZKcX+lZfD2cGt6gKaFE/ERGR/CjclLaI4eBTHVJPw9ZZRbp1dAfLwOKle+M4fj6tBIoTEREp/xRuSpvRCTpPsjxfOx2yC792Tb0gLzrW9sNkhm82RpdMfSIiIuWcwo0tNLsPvKtBShxs/6ZIt17aLXzephjSsnJKojoREZFyTeHGFhxdoNNEy/O1H0BOZqFv7V6vCuF+7iRl5PDTtpMlU5+IiEg5pnBjKy1GglcIJJ2E7d8W+jYHBwOjOoQDloHFJpOmhYuIiFxJ4cZWrmm9ySr0rXe3rIaniyPHzqSy+vCZkqlPRESknFK4saUWI8EzEBKPw865hb7Ny9WJoa1CAZi5LqqEihMRESmfFG5syckNOk60PF/zHuRmF/rW0R3CMRjgr0NnOHK6aHtViYiI2DOFG1trORo8AiAhGnZ9V+jbqvu506N+IACz1mtRPxERkUsUbmzN2R06PGF5vvpdyC389O6xHcMB+GnrSRLTCt/qIyIiYs8UbsqC1v8Adz+4EAl7fiz0be1r+VE/yIv07Fy+2xJTggWKiIiUHwo3ZYGzB3SYYHm++h0w5RbqNoPBwJiLrTdfrY8mJ9dUQgWKiIiUHwo3ZUXrB8HNF84dgT3zC33bgGZV8XV34mRCOsv3xZdggSIiIuWDwk1Z4eIF7cdZnheh9cbVych9basDmhYuIiICCjdlS5uHwdUHzh6EfT8X+rYH2oXj6GBgU9R59pxMLMECRUREyj6Fm7LE1QfaXWy9+ettMBVuDE2Qjyt3NAkG1HojIiKicFPWtH0EXLzhzH448Euhb7s0sPiXnac4k1z4jThFRETsjcJNWeNWCdo+anlehNab5tV9aV69Elm5Jmb/HV1y9YmIiJRxCjdlUbvHwNkL4vfAoSWFvm1MxxoAfLsxhsycwg1IFhERsTcKN2WRe2Vo+7Dl+ao3wWwu1G19GwcR5O3K2ZRMftsVW4IFioiIlF0KN2VVu3Hg5AFxu+DQ0kLd4mR04IH2YQB8uS4ScyFDkYiIiD1RuCmrPPygzYOW53+9VejWm+FtquPi6MCek0lsib5QggWKiIiUTTYNN6tXr6Z///6EhIRgMBhYuHBhoe9dt24djo6ONGvWrMTqs7n2E8DJHU5tgyMrCnVLZQ9nBjWvCsDMddotXEREKh6bhpvU1FQiIiL4+OOPi3RfQkICI0eOpEePHiVUWRnhGQCtxlqeF2HszeiL08J/3xPHiQtpJVSciIhI2WTTcNO3b19ef/11Bg0aVKT7Hn30Ue677z7at29fQpWVIR2eAEdXOLkFjv1ZqFvqB3nToZYfJjN8s0HTwkVEpGIpd2NuZs6cybFjx3j55ZdtXUrp8AqElmMsz1cVfuzN2IvTwuduiiEtK6ekqhMRESlzylW4OXz4MJMnT+bbb7/F0dGxUPdkZmaSlJSU51HudHwSjC5wfCNEri7ULbfVr0KYnztJGTnM33ayhAsUEREpO8pNuMnNzeW+++5j6tSp1K1bt9D3TZs2DR8fH+sjNDS0BKssId7B0HKU5flfbxfqFgcHA6PahwOWgcUmk6aFi4hIxWAwl5HFUAwGAwsWLGDgwIHXPZ+QkICvry9Go9F6zGQyYTabMRqNLFu2jNtuu+2a+zIzM8nMvLzXUlJSEqGhoSQmJuLt7V3s36PEJJ6ED5tBbhaM/g3COxV4S3JGNu2n/UFKZg5fjW1D17oBJV+niIhICUhKSsLHx6dQv7/LTcuNt7c3u3fvZseOHdbHo48+Sr169dixYwdt27a97n0uLi54e3vneZRLPlWh+f2W54VsvfFydeKeVtUATQsXEZGKw6bhJiUlxRpUACIjI9mxYwcxMTEATJkyhZEjRwLg4OBA48aN8zyqVKmCq6srjRs3xsPDw1Zfo/R0mgQOThD5F8RsLNQtozuEYzDAqoNnOHompYQLFBERsT2bhpstW7bQvHlzmjdvDsCkSZNo3rw5L730EgCxsbHWoCNApVBodp/l+V9vFeqWMD8PetSvAsCsdVElVJiIiEjZUWbG3JSWovTZlUkXouDDFmDOhX+sgNDWBd6y7shZRvz3b9ydjWyY0gMfN6eSr1NERKQY2eWYG7nINxwihluery7c2JsOtfyoF+hFWlYu328+XnK1iYiIlAEKN+VRl6fBYITDy+Dk1gIvNxgMjLm4JcOs9VHk5JpKuEARERHbUbgpjyrXhKZDLc//eqdQtwxsXhVfdydOJqSzYn98CRYnIiJiWwo35VXnp8HgAIeWQOzOAi93dTIyvE11AL7UwGIREbFjCjfllX8daDzE8ryQ69480D4MRwcDmyLPs/dUYgkWJyIiYjsKN+VZl2cBAxz4FeJ2F3h5sI8bfZsEAzBTrTciImKnFG7Ks4B60GiQ5fnqwo29uTSweNGOU5xJzsz/YhERkXJI4aa86/Ks5X/3/Qzx+wq8vEV1XyJCK5GVa2LO31ogUURE7I/CTXkX2BAaDrA8L2TrzdiLrTff/h1NVo6mhYuIiH1RuLEHl1pv9i6AMwcLvPyOJsEEertwJjmT33afKuHiRERESpfCjT0IagL17wTMsPrdAi93MjrwQLswAL5cG0UF24FDRETsnMKNvbjUerPnRzh7pMDLh7epjrOjA7tPJrI1+kIJFyciIlJ6FG7sRUgzqNsXzCZYU3DrjZ+nC4OaVQU0LVxEROyLwo096Xqx9WbX93DuaIGXj+kUDsDve+M4mZBegoWJiIiUHoUbe1K1JdTuBeZcWPt+gZfXD/KmfU0/ck1mvt4QVfL1iYiIlAKFG3vT9TnL/+6cBxeiCrx8bKcaAMzbdJy0rJwSLExERKR0KNzYm9DWUOs2MOXAmoJbb26rX4Xqld1JTM9mwfaTpVCgiIhIyVK4sUeXWm92zIGE/FchNjoYGNUhHLAMLNa0cBERKe8UbuxR9XZQowuYsmHt9AIvv6dVNTycjRw5ncKaw2dLvj4REZESpHBjry613mz/BhLz727ydnXinlahAMxcF1nSlYmIiJQohRt7Fd4JwjpBbhasm17g5aM7hGMwwJ8Hz3DsTErJ1yciIlJCFG7sWdd/Wv5361eQFJvvpeH+HtxWrwoAX62PKuHCRERESo7CjT2r0QVC20FuJqz/sMDLx3S0TAv/YesJEtOzS7o6ERGREqFwY88MhsutN1u+hOT4fC/vWNuPuoGepGXl8sOW46VQoIiISPFTuLF3tW6Daq0hJ6PA1huDwWBtvZm1PoqsHFNpVCgiIlKsFG7sncFweebUli8h5Uy+lw9sVhU/D2dOXEjn4z8L3l1cRESkrFG4qQhq94SQ5pCdBhs+yvdSN2cjr9zVCICP/zzCnpOJpVGhiIhIsVG4qQgMBug62fJ8038h9Vy+l9/ZNJi+jYPIMZl55oed6p4SEZFyReGmoqjbG4KaQnYqbPw430sNBgOvDWxMZQ9nDsQl89Efh0upSBERkVuncFNRXDn25u/PIe18vpf7e7rw2oDGAPxn1VF2n1D3lIiIlA8KNxVJvTsgsDFkJcPGTwq8vF/TYPo1DSbXZObpH3aQmZNbCkWKiIjcGoWbisTB4fK6N39/CukJBd7y6l2N8PNw5lB8Ch+uVPeUiIiUfQo3FU39/hDQADKT4O/PCrzcz9OF1wdauqc+/esYO48nlHCBIiIit0bhpqJxcICuz1qeb/wYMpIKvKVvk2D6R4SQe3H2VEa2uqdERKTsUripiBoOBP+6kJEImwpuvQGYelcj/D2dOXw6hX+re0pERMowhZuKyMEIXS6OvdnwMWQmF3hLZQ9nXh/YBIDP/jrK9pgLJVmhiIjITVO4qagaDwa/2pB+ATb/t1C39GkcxIBmIZjMqHtKRETKLIWbisrBCJ2fsTxf/xFkphTqtlf6NyLAy4WjZ1L5YPmhEixQRETk5ijcVGRN7gHfGpB2zrKpZiH4ejjzr0GW7qkv1hxja7S6p0REpGxRuKnIjI7Q5VLrzYeQlVao23o1DGRw86qYzPCsuqdERKSMUbip6JoOg0rVIfUMbJ1V6Nte7t+IKl4uHDubynvLDpZcfSIiIkWkcFPRGZ2g89OW5+umQ3Z6oW7zcXdi2mBL99R/10ayNTr/vapERERKi8KNQMR94BMKKfGw7etC39ajQSBDWlTDbIZnfthFepa6p0RExPYUbgQcnaHTU5bnaz+A7IxC3/pS/4YEersQeTaVd9U9JSIiZYDCjVg0vx+8QiA5FnZ8W+jbfNyceHNIUwC+XBfJpkh1T4mIiG0p3IiFo8vl1ps1H0BOZqFv7V6vCkNbWbqn/vnjTtKyckqoSBERkYIp3MhlLUaCZxAknYAdc4p06wt3NiTYx5Woc2m8/bu6p0RExHYUbuQyJ1foNNHyfM17lo01C8nb9XL31Kz1UWw8dq4EChQRESmYwo3k1XK0ZexN4nH47gHIySr0rV3rBnBv61AA/vnjLnVPiYiITdg03KxevZr+/fsTEhKCwWBg4cKF+V6/du1aOnbsiJ+fH25ubtSvX58PPvigdIqtKJzcYPhccPaEyL/g53FgMhX69uf7NSDEx5WY82m8teRACRYqIiJyfTYNN6mpqURERPDxxx8X6noPDw/Gjx/P6tWr2b9/Py+88AIvvPACn3/+eQlXWsGENIOhX4ODI+z+Hla+UuhbvVydeOtuS/fUVxui2XBU3VMiIlK6DGaz2WzrIgAMBgMLFixg4MCBRbpv8ODBeHh48M033xTq+qSkJHx8fEhMTMTb2/smKq1AdsyBhY9Znvd9G9o+Uuhbp8zfzdxNMVTzdWPpxC54uDiWUJEiIlIRFOX3d7kec7N9+3bWr19P165dbV2KfWp2H9z2ouX5kudg38+FvvX5fg2oWsmNExfSeVPdUyIiUorKZbipVq0aLi4utGrVinHjxvHggw/e8NrMzEySkpLyPKQIOj8NrcYCZvjpIYjeUKjbPF0cefti99Q3G6NZf+RsCRYpIiJyWbkMN2vWrGHLli18+umnTJ8+nblz597w2mnTpuHj42N9hIaGlmKldsBggDvehXr9IDcT5t4LZwq3jk3H2v7c3646AM/+uIuUTM2eEhGRklcuw02NGjVo0qQJDz30EE899RSvvPLKDa+dMmUKiYmJ1sfx48dLr1B74WCEIf+Faq0hIwG+HQJJsYW6dUrfBlTzdeNkQjr/Wry/ZOsUERGhnIabK5lMJjIzb7xVgIuLC97e3nkechOc3WH4d+BX27IGzuy7IaPgLj6PK7qn5vwdw9rD6p4SEZGSZdNwk5KSwo4dO9ixYwcAkZGR7Nixg5iYGMDS6jJy5Ejr9R9//DG//PILhw8f5vDhw/zvf//j3Xff5f7777dF+RWPhx/c/xN4VIH4PfDd/YVa5K9DLX9Gtg8D4LmfdpGckV3SlYqISAVm03CzZcsWmjdvTvPmzQGYNGkSzZs356WXXgIgNjbWGnTA0kozZcoUmjVrRqtWrfj444956623ePXVV21Sf4XkGw4jfijyIn/P9alP9cru6p4SEZESV2bWuSktWuemmBxZAXOGgSkHOk6EXlMLvGXjsXPc+/lGAL4e24YudQNKuEgREbEXFWadG7Gh2j3hro8sz9dNh78LXiW6XU0/RncIByzdU0nqnhIRkRKgcCM3r9l9cNsLludL/gn7FhV4yz/71CPMz53YxAze+FXdUyIiUvwUbuTWdH7mikX+HixwkT93Z0feuTsCgwG+23KcPw+eLp06RUSkwlC4kVtjXeTvjkIv8temRmXGdKgBwJSfdpOYru4pEREpPgo3cuscjDDkf0Va5O/Z3vWo4e9BXFIGr/26r3TqFBGRCkHhRorHpUX+Kte6uMjfPfku8ufmbOSdu5tiMMCPW0/wx4H4UixWRETs2U2Fm+PHj3PixAnr602bNjFx4kQ+/7zgGTNix6yL/AVA/O4CF/lrFV6Zf3S82D01fzeJaeqeEhGRW3dT4ea+++7jzz//BCAuLo5evXqxadMmnn/+eS2oV9FVrmFZ5M/Jo1CL/D3Tux41/T2IT8pk6q97S7FQERGxVzcVbvbs2UObNm0A+P7772ncuDHr169n9uzZzJo1qzjrk/IopDkM/RoMRtj9Pay88QJ/rk5G3rknAgcDzN92khX71D0lIiK35qbCTXZ2Ni4uLgCsWLGCu+66C4D69esTG1u43aLFztUp/CJ/LcN8eahzTQCmLNhNQlrB+1WJiIjcyE2Fm0aNGvHpp5+yZs0ali9fTp8+fQA4deoUfn5+xVqglGPNR0D3wi3y91SvutQK8OBMciZTf9HsKRERuXk3FW7eeustPvvsM7p168bw4cOJiIgAYNGiRdbuKhEAujwDLcdQ0CJ/rk5G3r3YPbVg+0mW7Y0r3TpFRMRu3PTGmbm5uSQlJeHr62s9FhUVhbu7O1WqVCm2AoubNs60gdwcy8ypQ0vAtRL8YxkE1LvupW8uOcCnfx3F39OF5U91wdfDuXRrFRGRMqnEN85MT08nMzPTGmyio6OZPn06Bw8eLNPBRmzE6Ah3fwlVWxW4yN/EnnWoU8WTsymZvLxIs6dERKTobircDBgwgK+//hqAhIQE2rZty3vvvcfAgQP55JNPirVAsRPO7nDf9wUu8nepe8roYGDRzlP8vkfdUyIiUjQ3FW62bdtG586dAfjxxx8JDAwkOjqar7/+mg8//LBYCxQ7cvUif98/cN1F/iJCK/FIF8vsqRcW7uZ8qmZPiYhI4d1UuElLS8PLywuAZcuWMXjwYBwcHGjXrh3R0dHFWqDYmSsX+Tu2ChaNh+sM+3qyZx3qBnpyNiWLl37eU/p1iohIuXVT4aZ27dosXLiQ48ePs3TpUm6//XYATp8+rUG6UrArF/nb9d11F/lzcTTy3j3NMDoY+HVXLIt3a/0kEREpnJsKNy+99BLPPPMM4eHhtGnThvbt2wOWVpzmzZsXa4Fip65c5G/tB7Dpi2suaVLNh8e71QLgxYV7OJeSWZoViohIOXXTU8Hj4uKIjY0lIiICBwdLRtq0aRPe3t7Ur1+/WIssTpoKXsb89Q78+TpggGHfQIP+eU5n5Zi4a8ZaDsQl069JMB+PaGGbOkVExKZKfCo4QFBQEM2bN+fUqVPWHcLbtGlTpoONlEFdnoGWo7Eu8hezMc9pZ0cH3r0nAkcHA7/tjuXXXadsUqaIiJQfNxVuTCYTr776Kj4+PoSFhREWFkalSpV47bXXMOWzA7TINQwGuOM9qNsXcjJgzjA4czDPJY2r+vB499oAvPTzXs6qe0pERPJxU+Hm+eefZ8aMGbz55pts376d7du3869//YuPPvqIF198sbhrFHt3zSJ/d0Ny3vVtxnevTYNgb86nZvHiwj3cZG+qiIhUADc15iYkJIRPP/3Uuhv4JT///DOPP/44J0+eLLYCi5vG3JRhqWfhf7fD+aMQ1ARGLwbXyz+jvacSGTBjHTkmMx8Ob85dESE2LFZEREpTiY+5OX/+/HXH1tSvX5/z58/fzFuKgIf/5UX+4q5d5K9RiA/jb7vUPbWH08kZtqpURETKsJsKNxEREcyYMeOa4zNmzKBp06a3XJRUYJVrWLZpuMEif+O616ZhsDcJadm8sEDdUyIicq2b6pb666+/6NevH9WrV7eucbNhwwaOHz/O4sWLrVszlEXqlionDi+3DC4250Knp6DnK9ZT+2OTuGvGWrJzzfz73mYMaFbVdnWKiEipKPFuqa5du3Lo0CEGDRpEQkICCQkJDB48mL179/LNN9/cVNEiedTpBXdd3KfsqkX+GgR788RtdQDL7KnTSeqeEhGRy256Eb/r2blzJy1atCA3N7e43rLYqeWmnPnrbfjzDa5e5C8718Sg/6xjz8kkejaowhcjW2EwGGxbq4iIlJhSWcRPpFR0efa6i/w5GR14755mOBkNrNh/mgXby+4MPRERKV0KN1K2XXeRv0MA1AvyYmLPugC8smgv8eqeEhERFG6kPDA6wt3/g6otLy7yN8S6yN8jXWrStJoPSRk5/N/83Zo9JSIiOBbl4sGDB+d7PiEh4VZqEbkxZw/LFPH/9YLzx2D23TB6MY6u3rx3TwT9PlzLygOn+WnbSe5uWc3W1YqIiA0VqeXGx8cn30dYWBgjR44sqVqlortmkb+RkJNFnUAvnupl6Z6a+ste4hLVPSUiUpEV62yp8kCzpezAyW0w607IToWm98KgT8kxmRny6QZ2Hk+gW70AZo5urdlTIiJ2RLOlxL5VbQFDvwKDEXbNg5Wv4mh04L17muLs6MCqg2f4YesJW1cpIiI2onAj5VOdXtD/35bna9+HTV9Qu4oXT1/snnrtl32cSki3YYEiImIrCjdSfrV4ALr9n+X54mdh/6882LkmzatXIjkzh8maPSUiUiEp3Ej51vWf0GIUlkX+/oHxxCbevScCF0cHVh86w/dbjtu6QhERKWUKN1K+GQzQ732o28eyyN/cYdQyxPLM7fUAeO3X/aw/ctbGRYqISGlSuJHyz+gId39pWeQv/QJ8O5ixEW60r+lHSmYOD3y5iS/XRqqLSkSkglC4EftwaZG/yjUhIQbj3KHMvK8+g5tXJddk5tVf9/HMD7vIyC67m7qKiEjxULgR+3FpkT93f4jbheuCMbw3pAEv3dkQo4OBn7adYNhnG4hN1CwqERF7pnAj9qVyTRjxPTi5w9E/MPw8jrGt/fl6bBt83Z3YeSKR/h+tY0vUeVtXKiIiJUThRuxP1ZZwz8VF/nb/AB80puOJ//LLg42pH+TF2ZRMhn+xkdl/R9u6UhERKQEKN2Kf6t4O984Bv9qWncRXTaParDb80mAFwxq6kp1r5vkFe5gyfzdZOSZbVysiIsVIe0uJfTPlwr6FsPo9OL0XALOjG7uCBvHI0Q7EmSvTMsyXT0a0oIq3q21rFRGRGyrK72+FG6kYTCY4tARWvwOntlsOOTjxg6kbH2XeSbZXNT57oBXNQivZtk4REbkuhZt8KNxUcGYzHF0Jq9+FmA0A5GBkQU5HvmAgDw28nXtahdq4SBERuZrCTT4UbsQqap2lJefYnwDkmg38ZmrHicaP89Ddd+Jk1JA0EZGyoii/v236t/fq1avp378/ISEhGAwGFi5cmO/18+fPp1evXgQEBODt7U379u1ZunRp6RQr9ie8I4xcCA+uxFy3D0aDmbuMG3h8/wNsf6cfCUf+tnWFIiJyE2wablJTU4mIiODjjz8u1PWrV6+mV69eLF68mK1bt9K9e3f69+/P9u3bS7hSsWvVWmG47zt4ZA1x1fpgMhtok7GeSt/eTvJ/B0DMRltXKCIiRVBmuqUMBgMLFixg4MCBRbqvUaNGDBs2jJdeeqlQ16tbSgoSdWAbh36cym3Zq3E0XJwmHt4ZujwDNbpaNusUEZFSVW66pW6VyWQiOTmZypUr3/CazMxMkpKS8jxE8hNevwVtn/6RKVVnMienO1lmI0Stga8HwP96waGlloHJIiJSJpXrcPPuu++SkpLC0KFDb3jNtGnT8PHxsT5CQzUTRgrm4+bEmw8O4ESnN+maOZ2ZOb3JMjjDic0wZyh81hn2/WyZYi4iImVKue2WmjNnDg899BA///wzPXv2vOF1mZmZZGZmWl8nJSURGhqqbikptF93neLZH3bhmX2OSV7LGGZehkNOmuWkfz1Ld1WjwWB0tG2hIiJ2zO67pebNm8eDDz7I999/n2+wAXBxccHb2zvPQ6Qo7mwawk+PdcDFN5gpyUPpmPUhRxo8Di4+cPYgzH8IZrSCbV9DTpatyxURqfDKXbiZO3cuY8aMYe7cufTr18/W5UgF0TDEm1/Gd6JjbT9is9zpub0TH0UswNT9RXCrDBciYdEE+LA5bPoCstNtXbKISIVl03CTkpLCjh072LFjBwCRkZHs2LGDmJgYAKZMmcLIkSOt18+ZM4eRI0fy3nvv0bZtW+Li4oiLiyMxMdEW5UsF4+vhzFdj2vBgpxoAvLc6jociu5L02Da4/Q3wDISkE7D4Gfh3BKz/CDJTbFy1iEjFY9MxN6tWraJ79+7XHB81ahSzZs1i9OjRREVFsWrVKgC6devGX3/9dcPrC0NTwaU4zN92gskXdxSvGeDBFyNbUauSI2z/BtZOt4QcsLTqtH8cWj8EbpVsWbKISLmm7RfyoXAjxWXXiQQe+WYrsYkZeLk4Mv3eZvRoEGgZd7PrO1jznqW7CsDFG9o+Am0fAw8/2xYuIlIOKdzkQ+FGitOZ5EzGzd7GpqjzGAwwqWddxt9WG4PBALk5sHcBrHkXzhyw3ODkAa3HQvsJ4BVo2+JFRMoRhZt8KNxIccvKMfHar/v4ZmM0AH0bB/HuPRF4uFycGm4ywYFfLZt0xu2yHDO6QMtR0OEJqKS1l0RECqJwkw+FGykp8zbF8OLPe8jONVMv0IvPR7YkzM/j8gVmMxxeDqvftiwGCODgBM2GQ6enoHJN2xQuIlIOKNzkQ+FGStLW6As89u1WTidn4uPmxIz7mtO5TkDei8xmiFxtacmJWmM5ZnCAxndD56ehSv3SL1xEpIxTuMmHwo2UtPikDB75Zis7jifgYIDJfevzUOealnE4V4vZCKvfhSPLLx4wQIP+llWPgyNKtW4RkbJM4SYfCjdSGjJzcnlx4R6+32KZEj6gWQhvDm6Km7Px+jec2m4JOQd+vXysTm/o8iyEti6FikVEyjaFm3wo3EhpMZvNfLMxmld/2UeOyUyjEG8+e6Al1Xzdb3xT/D7LFPK988F8cVPOGl2h8yQI7wwONwhHIiJ2TuEmHwo3Uto2HjvHuNnbOJeaRWUPZz6+rwXtaxWw1s3ZI7D2A9g1D0w5lmPu/lC3D9TrC7W6g7NH/u8hImJHFG7yoXAjtnAyIZ2Hv97C3lNJGB0MvHRnQ0a2D7v+OJwrXYiGdf+G3T9C5hXbjBhdoGZXS9Cp2we8Q0r2C4iI2JjCTT4UbsRW0rNymTJ/Fwt3nALgnpbVeG1gY1ydCtHVlJsN0evh4BI4uBgSovOeD24G9e6whJ2gJlBQaBIRKWcUbvKhcCO2ZDab+e+aSKYt2Y/JDBGhlfjs/pYE+bgW5U3g9H44tMQSdk5sAa74v7F3Nah3sfsqvDM4uhT79xARKW0KN/lQuJGyYM3hM4yfs53E9GwCvFz49P4WtAyrfHNvlhwPh5fCwd/h6B+Qk375nLMn1O4BdftCndu1r5WIlFsKN/lQuJGyIuZcGg9/s4UDcck4GQ28OqAxw9tUv7U3zU6HY39Zuq4O/Q4p8ZfPGRwgtJ2lRafeHeBf+9Y+S0SkFCnc5EPhRsqS1Mwcnv1xJ4t3xwEwom11Xu7fCGdHh1t/c5MJYrdfHKezBOL35D3vV/ty0KnWBoyOt/6ZIiIlROEmHwo3UtaYzWb+s+oo7y47iNkMrcN9+c+IlgR4FfNYmYQYS9fVwcUQtRZM2ZfPuVW2dFvV62vpxnLxKt7PFhG5RQo3+VC4kbLqjwPxPDl3B8mZOQR5u/LZAy2JCK1UMh+WkQhHVlq6rg4thYyEy+eMzpaByPX6Wh4+1UqmBhGRIlC4yYfCjZRlR8+k8PDXWzh6JhVnRwemDWrCkJYlHC5yc+D4xsvTzM8fy3s+qMnlaebBzTTNXERsQuEmHwo3UtYlZWQz6bsdrNh/GoAxHcN5/o4GOBqLYRxOQcxmOHvYEnIOLoETmy5vAwHgFXxxleQ7oEYXcCrCFHYRkVugcJMPhRspD0wmM9NXHubDlYcBaFezMq8NaEydwFIeC5N6Fg4vs4SdI39Adurlc07uUOs2S4tOnd7gGVC6tYlIhaJwkw+FGylPft8Ty6Tvd5KWlYvBAAMiQniyZ11q+NtgX6nsDIhac3n2VfKpK04aILTNxe0g+kJAPXVfiUixUrjJh8KNlDdHz6Tw1pIDLNtnWbPG6GBgUPOqPNmjDqGV89lhvCSZzRC70zIg+eBiy/Mr+da4PE6nejswOtmmThGxGwo3+VC4kfJq94lEPlhxiD8OWMbiODoYuKdVKBNuq01IJTfbFpd44mLQ+R0i/4LcrMvnXH2umGbe0/JaRKSIFG7yoXAj5d22mAt8sPwQaw6fBcDZ6MC9bUIZ1702gd5lYIBvZjIc/dPSdXV4KaSdu3zOYITgCAjrANXbWx7aEkJECkHhJh8KN2IvNkWe5/3lB9l47DwALo4O3N8ujEe71ir+BQBvlikXTmy+PPvq7KFrrwmobwk5lwJPpdDSr1NEyjyFm3wo3Ii9WX/kLO8tP8TW6AsAuDkZGdkhjEe61KKyh7ONq7tKwnGI2QDR6y2PswevvcanOoS1vxx4/OtqcLKIKNzkR+FG7JHZbGb14bO8v+wgO08kAuDhbGRspxo82KkmPu5ldEBv6jlL2LkUeGJ3gjk37zXu/pZByZdadoKaah8skQpI4SYfCjdiz8xmMyv3n+b95YfYF5sEgJerIw92qsnYTuF4uZbRkHNJZopl4cDoi4HnxGbIych7jbOnZdp59Q6WFp6qLcHJxgOqRaTEKdzkQ+FGKgKTycyyfXF8sPwwB+OTAajk7sTDXWoyqn04Hi7lpOUjJxNO7YCY9RcDz0bITMx7jdEZQlpc7MrqANXbakaWiB1SuMmHwo1UJCaTmd92xzJ9xSGOnrGsLuzn4cyjXWtxf7sw3JyNNq6wiEy5cHrfxaBzMfCkxF11kQECG1u6sS4FHq9Am5QrIsVH4SYfCjdSEeWazPy84yT/XnmY6HNpAAR4ufB4t1oMb1MdV6dyFnIuMZstG33GbLgceK7e+BOgcs2LY3YuBh7fGhqkLFLOKNzkQ+FGKrKcXBPzt1lCzsmEdACCfVwZ1702Q1uF4uxYCptzlrTkOMvg5EuBJ34PcNVfc55BF1t2Lg5SrtIQHOzgu4vYMYWbfCjciEBWjonvtxxnxh9HiEuyDNitWsmNJ3rUZnCLajiVxg7kpSU9AY7/fTnwnNwGpuy817j6QGi7y4EnuBk4lrFp9CIVnMJNPhRuRC7LyM5l3qYYPl51lDPJmQCE+bnzZI86DGhWFaODHXbdZKfDya2X19o5vinvbucAjm5QrdXllp1qrcHF0zb1igigcJMvhRuRa6Vn5TL772g+WXWUc6mWfaFqBngwsWdd7mwSjIM9hpxLcnMgbtfllp2YDXm3jIC820ZcCjzulW1Tr0gFpXCTD4UbkRtLzczhqw1RfL76GAlplq6beoFePNWrDrc3DLLvkHOJ2WzZJuJSy07MBkg8fu11PqEQ2OiKR2OoXEsLDIqUEIWbfCjciBQsOSObmeui+GLNMZIzcgBoGOzNpF516dGgCoaKNtPIum3EOssg5ettGwFgdIEq9S1B58rQ4+FfuvWK2CGFm3wo3IgUXmJaNv9de4wv10aSmmXZFiEitBKTetWlSx3/ihdyLklPsKy3E7/XMhsrfi/E77t27M4lnoF5w05gI8ueWY5lZINTkXJA4SYfCjciRXc+NYvPVx/jq/VRpGdbQk6rMF8m9apLh9pqlQDAZIKEqItB51Lo2Xdx3Z3r/DXr4GgJOFeHHq9grcEjch0KN/lQuBG5eWeSM/nsr6N8szGazBwTAO1qVmZSr3q0qaEBtteVlQqnD1zRwrMX4ndDRuL1r3fzzdutVaWRpavL2aN06xYpYxRu8qFwI3Lr4pMy+M+fR5i76ThZuZaQ07mOP5N61aV5dV8bV1cOmM2QdOqqbq29loHMV++KDoDBssrylS08gY2gUpgWH5QKQ+EmHwo3IsXnZEI6H/95hO83HyfHZPmr5Lb6VXiqZ12aVNPmlUWWnWEJOFeHntTT17/e2dOyunKerq2G2jhU7JLCTT4UbkSK3/HzaXy48jDzt58k92LIub1hIE/1qkuDYP3/7JalnL6iS+ti8DlzAHKzrn+9T/Vrp6n71QKHcrqHmAgKN/lSuBEpOZFnU/lw5WEW7jjJpb9Z+jUJZmLPOtQJ9LJtcfYmNxvOHb1qLM9eSDpx/esdXSHgetPU/Uq3bpGbpHCTD4UbkZJ35HQyH6w4zG+7YgHL5J8BESE82bMuNfw1MLZEpV+wzNK6smvr9D7ITrv+9Xl2TO8AvuGarSVlksJNPhRuRErPgbgkPlh+iKV74wFwMMBt9QO5v111utQJqBgrHpcFJhNciLxqmvpey7GreQVf3mIirKOltUeDlqUMULjJh8KNSOnbczKR95cf4o8DlwfGVq/szn1tq3NPy2r4eWoxO5tIT7BsHBq9Lp8d0ytdDDqXdkyPAKOTLaqVCk7hJh8KNyK2c+R0CrP/jubHrSes2zo4Gx24o0kQ97cLo2WYb8Vd9bgsyEq7vGN6zKUd06/qznJyt+ySHtYRwtpD1Vbg7G6beqVCUbjJh8KNiO2lZ+Xyy85TfPt3NLtOXF7Mrn6QFyPahTGwWQhermodsLncbIjddbllJ2aDZUzPlRycIKT55Zad0LbgVskm5Yp9U7jJh8KNSNmy60QC326MZtHOU2RkWxYE9HA2MqB5Ve5vG0bDEP3/tMwwmSxT0GPWX941PTn2qosMlllYYe0vD1T2CrRJuWJfyk24Wb16Ne+88w5bt24lNjaWBQsWMHDgwBteHxsby9NPP82WLVs4cuQITzzxBNOnTy/SZyrciJRNiWnZ/LTtBLP/jubomcsbULYM8+X+dtXp2zgYVyet01KmmM1wISrvjunnj157XeVaF8NOR8v4Hc3IkptQlN/fjqVU03WlpqYSERHB2LFjGTx4cIHXZ2ZmEhAQwAsvvMAHH3xQChWKSGnxcXdibKcajOkYzoZj55i9MYale+PYGn2BrdEXePWXfQxtFcp9basT5qfp5GWCwQCVa1geze6zHEuOuxh21lvCTvweS+A5fxS2f2u5xiskb8uOZmRJMSsz3VIGg6HAlpsrdevWjWbNmqnlRsSOnU7K4LvNx5m7KYZTiRnW413qBjCibXV61K+Co1G/FMu09AQ4/vflbqxT26+dkeXma2nRuTT9PLipZmTJNcpNy01pyMzMJDMz0/o6KSnJhtWISFFU8XZlQo86PNatFn8ePMO3G6NZffgMqw9ZHsE+rtzbujr3tgkl0NvV1uXK9bhVgrq9LQ+4OCNri6VVJ3odnNhsGaR8cLHlAeDkAaGtLy8sWK0VOLnZ7CtI+WP34WbatGlMnTrV1mWIyC1wNDrQq2EgvRoGEnMujdmbovlhywliEzP4YMUhPvrjML0aBnJ/uzA61PLTdPKyzNkdanSxPODijKydl1t2YjZARgIcW2V5gGVGVtUWl1t2QttoRpbky+67pa7XchMaGqpuKZFyLjMnlyW74/h2YzRboi9PT67p73FxccBQfNzVtVHumExwZn/esHPDGVkdLGN3NCOrQlC31BVcXFxwcdHqpyL2xsXRyMDmVRnYvCoH4pKYvTGGBdtPcuxsKq//tp93lh6kf0QI97cLI6Kaj1pzygsHh8sbe7Z56OKMrMiL3VgXFxc8fwzid1semz6z3OfiDV5Blu0jvILBO/jy80uvPQM1lqeCsPtwIyL2r36QN68NbMxzfevz846TfLsxhv2xSfy49QQ/bj1B46re3N82jLuaheDurL/2yhWDwbK5Z+Wa0HyE5Vhy3OVWnej1ln2yMpMsj7OH8nsz8Ai4HIKuF4C8gsHdT1PVyzmbdkulpKRw5MgRAJo3b877779P9+7dqVy5MtWrV2fKlCmcPHmSr7/+2nrPjh07AHjwwQepV68ezz77LM7OzjRs2LBQn6nZUiL2z2w2sy0mgdkbo/l1dyxZOZbFAb1cHRnSohoj2lanTqCXjauUYpOZAkmnLN1Xlx5JVzxPjrP8rymncO9ndAbPIEsIulEA8goGF8+S/V6SR7lZxG/VqlV07979muOjRo1i1qxZjB49mqioKFatWmU9d72m5bCwMKKiogr1mQo3IhXL+dQsftx6nNl/xxB97vI+SW1rVOb+dmH0bhSEs6Omk9s9kwnSzkHyqcthJ08Auvg67Wzh39PZ62LYCbpxAPIMBEfnkvteFUi5CTe2oHAjUjGZTGbWHjnLtxujWbE/HtPFv/n8PV0Y1roaw9tUp5qvNoCs8HKyICXOEoCSrghCeVqE4iArufDvae0KC7lxl5i7nxYyLIDCTT4UbkQkNjGduZuOM29TDKeTLbMpHQzQvV4V7m8XRpe6ARgdNOZC8pGZfFUAurpF6FJXWHbB7wWW6e5eQVAp7OKqzzWveNQAF3WjKtzkQ+FGRC7JzjWxYl883/4dzboj56zHq/m6cV/b6gxtFYq/p2Zbyk0ymSD9/LUB6OrXqWcKfi/PwLxh58rw4+pT8t+lDFC4yYfCjYhcz7EzKcz+O4Yft54gMd3yr20no4G+jYO5v10YrcN9NZ1cSkZOFqTEW0JPQrRlqvulx7mjloCUH3c/y+akeVp7LoYg98ql8x1KgcJNPhRuRCQ/Gdm5/LLzFN/+HcPO4wnW43UDPbm/XRiDmlfFy1VrpUgpSr8A5yMvBp7IvOEn9XT+97pWsgQdv+uEn3I25V3hJh8KNyJSWHtOJvLtxmh+3nGK9OxcANydjQxoVpUhLarSorovDhqbI7aUkWRZ5PDKwHMpAF2zsvNVXLyv6OK6Kvx4VilzwUfhJh8KNyJSVEkZ2czfeoJv/47hyOkU6/Gqldy4s2kw/SNCaBTirW4rKVuyUuFClKVr6+rwk3Qi/3udPC53bV3d6uMZZJOZXQo3+VC4EZGbZTab2RR5nu+2HGfZ3nhSMi8vClczwIO7IkK4KyKEmgFa3E3KuOx0uHDl+J4rAlDiCTCbbnyvo9sVLT418rb6eFctseCjcJMPhRsRKQ4Z2bn8eeA0i3aeYuWB09ZVkAEaV/XmrogQ7mwaQkglNxtWKXITcjIhIeaq1p6Lg5sTYsCce+N7jS7gGw5+tWHYt8UadBRu8qFwIyLFLTkjm+X74lm08xRrDp8l13T5r9U24ZXpHxHMHU2C8dO0cinvcrMvBp+rx/kcs3SBXVrXx6c6PLW7WD9a4SYfCjciUpLOp2axeHcsi3aeYnPUeS79DWt0MNCxtj93RYTQu1GgZlyJ/cnNsYzlOX/M0u1Vv1+xvr3CTT4UbkSktMQmpvPrTkvQ2X0y0Xrc2dGB2+pV4a5mIdxWvwquTkYbVilSPijc5EPhRkRsIfJsKr/sPMWinafyzLjycDZye6Mg7ooIoVMdf5yM2l9I5HoUbvKhcCMitmQ2m9kfm8yinaf4ZecpTiakW8/5ujvRt0kwd0WE0Ca8stbQEbmCwk0+FG5EpKwwm81si7nAoh2n+G13LGdTsqzngrxdrWvoNK3mozV0pMJTuMmHwo2IlEU5uSY2HjvPop0nWbInjuSMy2vohPu50//iGjp1ArU7tFRMCjf5ULgRkbIuMyeXvw6eYdHOU6zYH09G9uU1dOoHeXFXsxD6Nw0htLK7DasUKV0KN/lQuBGR8iQ1M4cV++NZtOMUqw+fITv38l/ZzatX4q6IEPo1DaaKl6sNqxQpeQo3+VC4EZHyKiEti9/3xLFo5yk2HDtnXUPHwQDta/lxV0QIfRoF4+OuNXTE/ijc5EPhRkTswemkDH7dZVlDZ8fxBOtxJ6OBrnUta+j0bFAFd2dH2xUpUowUbvKhcCMi9ibmXBq/7LJMLT8Ql2w97uZkpGfDQO6KCKFr3QCcHbWGjpRfCjf5ULgREXt2KD6ZRTssiwXGnE+zHvd2daRv42DuahZCu5p+GLWGjpQzCjf5ULgRkYrAbDaz80Qii3ac4tddpzidnGk9F+DlQr8mlqDTrFolLRYo5YLCTT4UbkSkosk1mfk78hy/7IxlyZ5YEtKyrecCvV3o2SCQ2xsF0a5mZVwctc+VlE0KN/lQuBGRiiwrx8TaI2dYtOMUy/fFk5qVaz3n6eJI13oB3N4wkG71quDjpllXUnYo3ORD4UZExCIjO5cNR8+xbF88K/bHc+aKritHBwNta1bm9oZB9GwYSNVKbjasVEThJl8KNyIi1zKZzOw8kcDyffEs3xfP4St2LgdoFOJNr4aB9GoYSMNgb+11JaVO4SYfCjciIgWLPJvK8n1xLN8Xz9boC5iu+E1RtZIbvRoGcnvDQFrXqIyTUVPMpeQp3ORD4UZEpGjOpWSy8sBplu+LZ83hM3n2uvJ2deS2+lXo1TCIrvUC8HTRooFSMhRu8qFwIyJy89Kzcll75CzL9sax8sBpzqdmWc85Gx3oUNvP0n3VIJAq3trvSoqPwk0+FG5ERIpHrsnMtpgL1nE6kWdT85yPCK3E7RfH6dSp4qlxOnJLFG7yoXAjIlL8zGYzR8+ksHSvJehcud8VQJif+8WgE0TLMF+tkCxFpnCTD4UbEZGSdzopgxX7T7N8Xxzrjp4jK+fyOJ3KHs4Xx+kE0qVOAG7OWjhQCqZwkw+FGxGR0pWamcPqQ2dYti+ePw6cJjH98grJLo4OdK5jWTjwtgZV8Pd0sWGlUpYp3ORD4UZExHayc01sjjpvHadz4kK69ZzBAC2r+1rX06kZ4GnDSqWsUbjJh8KNiEjZYDabORCXbA06u08m5jlfK8CD2xsF0athoDb4FIWb/CjciIiUTacS0lmx3xJ0Nhw9R84VKwcGeLnQs4FlnE6HWv64OmmcTkWjcJMPhRsRkbIvKSObVQfPsHxfPKsOnCY5M8d6zt3ZSJc6AdzeKJDb6lehkruzDSuV0qJwkw+FGxGR8iUrx8TfkedYtteywWdsYob1nNHBQOtwX7rVq0Kn2v40DPZW95WdUrjJh8KNiEj5ZTab2XMyieX74li2L54Dccl5zlf2cKZDLT861fanUx1/qvm626hSKW4KN/lQuBERsR/Hz6exYn88646cZcPRc6Rm5eY5H+7nTqc6/nSq7U/7Wv74uDnZqFK5VQo3+VC4ERGxT9m5JnYeT2DN4bOsO3KW7ccTyL1iULKDAZpUq0Tn2v50rO1Pi7BKuDhqYHJ5oXCTD4UbEZGKITkjm7+PnWftkbOsOXyGo2fy7n3l5mSkTY3KdK5jCTv1g7y0/1UZpnCTD4UbEZGKKTYxnbUXW3XWHjnH2ZTMPOf9PV3oWPvyeJ1gHzcbVSrXo3CTD4UbERExm80cjE9m7eGzrD1ylr+PnSc9O+94nVoBHheDTgDtalbGy1XjdWxJ4SYfCjciInK1rBwT22IusO7IWdYcPsuuEwlcMVwHo4OBZqGV6Fjbn851/GkWWgkno4PtCq6AFG7yoXAjIiIFSUzPZsPRcxe7sM4SeTbveB0PZyPtavpZw07tKp4ar1PCFG7yoXAjIiJFdeJCmnWszrojZzmfmpXnfKC3Cx1rW6acd6rtTxVvVxtVar8UbvKhcCMiIrfCZDKzPy7JOl5nU+R5MnNMea6pG+hJp9oBdKrjR9safni4ONqoWvuhcJMPhRsRESlOGdm5bIu+wJojlplYu08mcuVvVkcHAy2q+9Lp4pTziGo+OGq8TpGVm3CzevVq3nnnHbZu3UpsbCwLFixg4MCB+d6zatUqJk2axN69ewkNDeWFF15g9OjRhf5MhRsRESlJF1Kz2HDsnHUxwZjzaXnOe7k40q6Wn3V9nZr+HhqvUwhF+f1t03ay1NRUIiIiGDt2LIMHDy7w+sjISPr168ejjz7K7NmzWblyJQ8++CDBwcH07t27FCoWERHJn6+HM3c0CeaOJsEAxJxLY+2Rs6w9coZ1R86RmJ7N8n3xLN8XD0CIj6tlvE4dfzrU8ifAy8WW5duFMtMtZTAYCmy5ee655/jtt9/Ys2eP9di9995LQkICv//+e6E+Ry03IiJiK7kmM3tPJVrCzuGzbIm6QFZu3vE69QK96FDbj461/Gmr9XWsyk3LTVFt2LCBnj175jnWu3dvJk6ceMN7MjMzycy8vAplUlJSSZUnIiKSL6ODgabVKtG0WiUe71ab9KxcNkedt66vsy82iYPxyRyMT2bmuqiL1/vQqbalVUf7YRVOuQo3cXFxBAYG5jkWGBhIUlIS6enpuLldu1T2tGnTmDp1ammVKCIiUmhuzka61A2gS90ApgDnU7Ms6+scPcv6I2eJOpfG9pgEtsck8NEfR3B1cqB1eGU61PKnY20/GoX4YHTQeJ2rlatwczOmTJnCpEmTrK+TkpIIDQ21YUUiIiLXV9nDmX5Ng+nX1DJe52RCOuuOWILOuqPnOJOcyZrDllYeAG9XR9rXsiwm2KGWP7UCNDgZylm4CQoKIj4+Ps+x+Ph4vL29r9tqA+Di4oKLiwZniYhI+VO1khtDW4UytFUoZrOZI6dTrIsJ/n3sHEkZOSzdG8/SvZbfjYHeLnSs5U+H2paWnYq6+We5Cjft27dn8eLFeY4tX76c9u3b26giERGR0mEwGKgT6EWdQC9Gd6xBTq6J3ScTWX9xm4gt0ReIT8pk/vaTzN9+EoCa/h7Wwcnta/lRyd3Zxt+idNh0tlRKSgpHjhwBoHnz5rz//vt0796dypUrU716daZMmcLJkyf5+uuvActU8MaNGzNu3DjGjh3LH3/8wRNPPMFvv/1W6Kngmi0lIiL2KCM7l63Rls0/1x09x+6rNv80GKBRiDcda/vTsZY/rcMr4+ZcfgYnl5tF/FatWkX37t2vOT5q1ChmzZrF6NGjiYqKYtWqVXnueeqpp9i3bx/VqlXjxRdf1CJ+IiIiV0lMz+bvY+dYf/Qca4+c5cjplDznnY0ONK9u2em8Y20/mlYr2zudl5twYwsKNyIiUhHFJ2Ww/uhZ1h05x/ojZzmVmJHnvIezkbY1/ehwcYByvUAvHMrQTCyFm3wo3IiISEVnNpuJOmfZ6Xz90bNsOHqOC2nZea7x83C2zsTqWMuf6n7uNqrWQuEmHwo3IiIieZlMZvbFJllbdjZFnic9OzfPNdV83ehYy5+OdfzpUMsPf8/SnYmscJMPhRsREZH8ZeWY2HE8wdqysz0mgRxT3rhQP8jLuphgmxolv02Ewk0+FG5ERESKJjUzh02R560zsfbH5t3KyOhgIKKaj3UxwZLYJkLhJh8KNyIiIrfmXEomG46dswxOPnqW6HNpec57OBvZ+mIvXJ2KL+DY7caZIiIiYnt+ni7c2TSEO5uGAHDiQhrrj1j2xFp35BxVfd2KNdgUlcKNiIiI3JJqvu4Mbe3O0NaWbSKunnlV2sruaj0iIiJS7hgMBip72HabB4UbERERsSsKNyIiImJXFG5ERETErijciIiIiF1RuBERERG7onAjIiIidkXhRkREROyKwo2IiIjYFYUbERERsSsKNyIiImJXFG5ERETErijciIiIiF1RuBERERG74mjrAkqb2WwGICkpycaViIiISGFd+r196fd4fipcuElOTgYgNDTUxpWIiIhIUSUnJ+Pj45PvNQZzYSKQHTGZTJw6dQovLy8MBkOxvndSUhKhoaEcP34cb2/vYn1vKTr9PMoW/TzKHv1Myhb9PPJnNptJTk4mJCQEB4f8R9VUuJYbBwcHqlWrVqKf4e3trf8wyxD9PMoW/TzKHv1Myhb9PG6soBabSzSgWEREROyKwo2IiIjYFYWbYuTi4sLLL7+Mi4uLrUsR9PMoa/TzKHv0Mylb9PMoPhVuQLGIiIjYN7XciIiIiF1RuBERERG7onAjIiIidkXhRkREROyKwk0x+fjjjwkPD8fV1ZW2bduyadMmW5dUYU2bNo3WrVvj5eVFlSpVGDhwIAcPHrR1WXLRm2++icFgYOLEibYupcI6efIk999/P35+fri5udGkSRO2bNli67IqpNzcXF588UVq1KiBm5sbtWrV4rXXXivU/klyYwo3xeC7775j0qRJvPzyy2zbto2IiAh69+7N6dOnbV1ahfTXX38xbtw4Nm7cyPLly8nOzub2228nNTXV1qVVeJs3b+azzz6jadOmti6lwrpw4QIdO3bEycmJJUuWsG/fPt577z18fX1tXVqF9NZbb/HJJ58wY8YM9u/fz1tvvcXbb7/NRx99ZOvSyjVNBS8Gbdu2pXXr1syYMQOw7F8VGhrKhAkTmDx5so2rkzNnzlClShX++usvunTpYutyKqyUlBRatGjBf/7zH15//XWaNWvG9OnTbV1WhTN58mTWrVvHmjVrbF2KAHfeeSeBgYH873//sx4bMmQIbm5ufPvttzasrHxTy80tysrKYuvWrfTs2dN6zMHBgZ49e7JhwwYbViaXJCYmAlC5cmUbV1KxjRs3jn79+uX5/4qUvkWLFtGqVSvuueceqlSpQvPmzfniiy9sXVaF1aFDB1auXMmhQ4cA2LlzJ2vXrqVv3742rqx8q3AbZxa3s2fPkpubS2BgYJ7jgYGBHDhwwEZVySUmk4mJEyfSsWNHGjdubOtyKqx58+axbds2Nm/ebOtSKrxjx47xySefMGnSJP7v//6PzZs388QTT+Ds7MyoUaNsXV6FM3nyZJKSkqhfvz5Go5Hc3FzeeOMNRowYYevSyjWFG7Fr48aNY8+ePaxdu9bWpVRYx48f58knn2T58uW4urraupwKz2Qy0apVK/71r38B0Lx5c/bs2cOnn36qcGMD33//PbNnz2bOnDk0atSIHTt2MHHiREJCQvTzuAUKN7fI398fo9FIfHx8nuPx8fEEBQXZqCoBGD9+PL/++iurV6+mWrVqti6nwtq6dSunT5+mRYsW1mO5ubmsXr2aGTNmkJmZidFotGGFFUtwcDANGzbMc6xBgwb89NNPNqqoYnv22WeZPHky9957LwBNmjQhOjqaadOmKdzcAo25uUXOzs60bNmSlStXWo+ZTCZWrlxJ+/btbVhZxWU2mxk/fjwLFizgjz/+oEaNGrYuqULr0aMHu3fvZseOHdZHq1atGDFiBDt27FCwKWUdO3a8ZmmEQ4cOERYWZqOKKra0tDQcHPL+KjYajZhMJhtVZB/UclMMJk2axKhRo2jVqhVt2rRh+vTppKamMmbMGFuXViGNGzeOOXPm8PPPP+Pl5UVcXBwAPj4+uLm52bi6isfLy+ua8U4eHh74+flpHJQNPPXUU3To0IF//etfDB06lE2bNvH555/z+eef27q0Cql///688cYbVK9enUaNGrF9+3bef/99xo4da+vSyjVNBS8mM2bM4J133iEuLo5mzZrx4Ycf0rZtW1uXVSEZDIbrHp85cyajR48u3WLkurp166ap4Db066+/MmXKFA4fPkyNGjWYNGkSDz30kK3LqpCSk5N58cUXWbBgAadPnyYkJIThw4fz0ksv4ezsbOvyyi2FGxEREbErGnMjIiIidkXhRkREROyKwo2IiIjYFYUbERERsSsKNyIiImJXFG5ERETErijciIiIiF1RuBGRCslgMLBw4UJblyEiJUDhRkRK3ejRozEYDNc8+vTpY+vSRMQOaG8pEbGJPn36MHPmzDzHXFxcbFSNiNgTtdyIiE24uLgQFBSU5+Hr6wtYuow++eQT+vbti5ubGzVr1uTHH3/Mc//u3bu57bbbcHNzw8/Pj4cffpiUlJQ813z55Zc0atQIFxcXgoODGT9+fJ7zZ8+eZdCgQbi7u1OnTh0WLVpkPXfhwgVGjBhBQEAAbm5u1KlT55owJiJlk8KNiJRJL774IkOGDGHnzp2MGDGCe++9l/379wOQmppK79698fX1ZfPmzfzwww+sWLEiT3j55JNPGDduHA8//DC7d+9m0aJF1K5dO89nTJ06laFDh7Jr1y7uuOMORowYwfnz562fv2/fPpYsWcL+/fv55JNP8Pf3L70/ABG5eWYRkVI2atQos9FoNHt4eOR5vPHGG2az2WwGzI8++miee9q2bWt+7LHHzGaz2fz555+bfX19zSkpKdbzv/32m9nBwcEcFxdnNpvN5pCQEPPzzz9/wxoA8wsvvGB9nZKSYgbMS5YsMZvNZnP//v3NY8aMKZ4vLCKlSmNuRMQmunfvzieffJLnWOXKla3P27dvn+dc+/bt2bFjBwD79+8nIiICDw8P6/mOHTtiMpk4ePAgBoOBU6dO0aNHj3xraNq0qfW5h4cH3t7enD59GoDHHnuMIUOGsG3bNm6//XYGDhxIhw4dbuq7ikjpUrgREZvw8PC4ppuouLi5uRXqOicnpzyvDQYDJpMJgL59+xIdHc3ixYtZvnw5PXr0YNy4cbz77rvFXq+IFC+NuRGRMmnjxo3XvG7QoAEADRo0YOfOnaSmplrPr1u3DgcHB+rVq4eXlxfh4eGsXLnylmoICAhg1KhRfPvtt0yfPp3PP//8lt5PREqHWm5ExCYyMzOJi4vLc8zR0dE6aPeHH36gVatWdOrUidmzZ7Np0yb+97//ATBixAhefvllRo0axSuvvMKZM2eYMGECDzzwAIGBgQC88sorPProo1SpUoW+ffuSnJzMunXrmDBhQqHqe+mll2jZsiWNGjUiMzOTX3/91RquRKRsU7gREZv4/fffCQ4OznOsXr16HDhwALDMZJo3bx6PP/44wcHBzJ07l4YNGwLg7u7O0qVLefLJJ2ndujXu7u4MGTKE999/3/peo0aNIiMjgw8++IBnnnkGf39/7r777kLX5+zszJQpU4iKisLNzY3OnTszb968YvjmIlLSDGaz2WzrIkRErmQwGFiwYAEDBw60dSkiUg5pzI2IiIjYFYUbERERsSsacyMiZY56y0XkVqjlRkREROyKwo2IiIjYFYUbERERsSsKNyIiImJXFG5ERETErijciIiIiF1RuBERERG7onAjIiIidkXhRkREROzK/wM9wPj2oA7ajgAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "def plot_metrics(history):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + " plt.figure()\n", + " plt.plot(history.history['loss'], label='Training Loss')\n", + " plt.plot(history.history['val_loss'], label='Validation Loss')\n", + " plt.xlabel('Epochs')\n", + " plt.ylabel('Loss')\n", + " plt.title('Training vs. Validation Loss')\n", + " plt.legend()\n", + " \n", + " plt.figure()\n", + " plt.plot(history.history['categorical_accuracy'], label='Categorical Accuracy')\n", + " plt.plot(history.history['val_categorical_accuracy'], label='Validation Categorical Accuracy')\n", + " plt.xlabel('Epochs')\n", + " plt.ylabel('Categorical Accuracy')\n", + " plt.title('Training vs. Validation Categorical Accuracy')\n", + " \n", + " plt.show()\n", + " #raise NotImplementedError()\n", " \n", "plot_metrics(history_basic)" ] @@ -1395,7 +1489,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The loss decreased over time and the accuracy increased as desired. However in both cases the effect was greater for the training data than for the validation set." ] }, { @@ -1437,7 +1531,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The difference between the training and validation sets for the loss and accuracy would increase. This would imply overfitting of the model as it becomes increasingly better at predicting samples from the training set than the validation set." ] }, { @@ -1463,7 +1557,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "id": "f22e89cb", "metadata": { "deletable": false, @@ -1482,7 +1576,9 @@ "source": [ "def model_predict(model, x):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + " predicted_targets_one_hot = model.predict(x)\n", + " predicted_targets = np.array([np.where(one_hot==np.max(one_hot))[0][0] for one_hot in predicted_targets_one_hot])\n", + " #raise NotImplementedError()\n", " return predicted_targets" ] }, @@ -1511,7 +1607,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "id": "3565c7b9", "metadata": { "deletable": false, @@ -1526,15 +1622,25 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step \n" + ] + } + ], "source": [ "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "test_targets = np.array([np.where(one_hot==1)[0][0] for one_hot in y_test])\n", + "test_targets_basic = np.array(model_predict(model_basic, x_test))\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "id": "a7f97fbb", "metadata": { "deletable": false, @@ -1551,7 +1657,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "test_targets defined.\n", + "test_targets_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('test_targets')\n", "check_var_defined('test_targets_basic')\n", @@ -1583,7 +1698,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "id": "c5047120", "metadata": { "deletable": false, @@ -1598,11 +1713,53 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average Recall: 0.618, Average Precision 0.642\n" + ] + } + ], "source": [ "def average_recall_precision(y, y_predict):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + "\n", + " precision = 0\n", + " recall = 0\n", + " \n", + " classes = set(y)\n", + " \n", + " for c in classes:\n", + " true_positives = 0\n", + " false_positives = 0\n", + " false_negatives = 0\n", + "\n", + " for truth, prediction in zip(y, y_predict):\n", + "\n", + " # Element is irrelevant for this class\n", + " if truth != c and prediction != c:\n", + " continue\n", + "\n", + " if truth == prediction:\n", + " true_positives += 1\n", + " elif truth == c:\n", + " false_negatives += 1\n", + " elif prediction == c:\n", + " false_positives += 1\n", + "\n", + " \n", + " precision_class = true_positives / (true_positives + false_positives) \n", + " recall_class = true_positives / (true_positives + false_negatives)\n", + " \n", + " precision += precision_class\n", + " recall += recall_class\n", + " \n", + " precision /= len(classes)\n", + " recall /= len(classes)\n", + " \n", + " #raise NotImplementedError()\n", "\n", " print(f\"Average Recall: {recall:.3f}, Average Precision {precision:0.3f}\")\n", " return recall, precision\n", @@ -1612,7 +1769,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "id": "5d9aae79", "metadata": { "deletable": false, @@ -1629,7 +1786,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "recall_basic defined.\n", + "precision_basic defined.\n" + ] + } + ], "source": [ "check_var_defined('recall_basic')\n", "check_var_defined('precision_basic')" @@ -1680,7 +1846,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "id": "1b4795f7", "metadata": { "deletable": false, @@ -1696,13 +1862,27 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n", "\n", "def plot_confusion_matrix(y, y_pred, title=\"\"):\n", " # YOUR CODE HERE\n", - " raise NotImplementedError()\n", + " cm = confusion_matrix(y, y_pred, normalize=\"true\") * 100\n", + " display = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=labels)\n", + " display.plot(cmap=\"Greens\", values_format=\".1f\")\n", + " #raise NotImplementedError()\n", " plt.title(title)\n", " plt.show()\n", "\n", @@ -1748,7 +1928,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The average recall and precision are balanced, suggesting the model is equally good at minimising false positives as false negatives. Some information is lost in these averages, as we can see from the confusion matrix that the model performs much better for the sunflowers class as for the others with >92% accuracy. Roses are frequently misidentified as tulips, suggesting the model's precision for roses may be low." ] }, { @@ -1794,7 +1974,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Dropout layers set a random amount of the training data to zero in each epoch, forcing the model to generalise by providing effectively different training data each time. It becomes harder for the model to fit specifically to instances in the training data because it cannot see all of the training data at once." ] }, { @@ -1838,7 +2018,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Data augmentation is the process of applying small variations to the training data, for example rotating, cropping, flipping training or slightly altering the colours. This similarly limits the model's ability to fit specifically to the training data as it is operating on a modified version, instead of the training data itself, forcing it to generalise." ] }, { @@ -1864,7 +2044,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "id": "cae90829", "metadata": { "deletable": false, @@ -1880,18 +2060,45 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/ktyl/.conda/envs/mlbd/lib/python3.11/site-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", + " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" + ] + } + ], "source": [ "tf.keras.backend.clear_session()\n", "tf.keras.utils.set_random_seed(48263)\n", "\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_dropout = tf.keras.models.Sequential([\n", + " tf.keras.layers.RandomZoom(0.1, seed=42),\n", + " tf.keras.layers.RandomRotation(0.1, seed=42),\n", + " tf.keras.layers.RandomFlip(\"horizontal\", seed=42),\n", + " tf.keras.layers.Conv2D(filters=8, kernel_size=(3,3), activation=\"relu\", input_shape=(224,224,3)),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=16, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation=\"relu\"),\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Flatten(),\n", + " tf.keras.layers.Dense(32, activation=\"relu\"),\n", + " tf.keras.layers.Dropout(0.5),\n", + " tf.keras.layers.Dense(5, activation=\"softmax\")\n", + "])\n", + "\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "id": "77868aae", "metadata": { "deletable": false, @@ -1908,12 +2115,230 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model_dropout defined.\n" + ] + }, + { + "data": { + "text/html": [ + "
Model: \"sequential\"\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1mModel: \"sequential\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ random_zoom (RandomZoom)        │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ random_rotation                 │ ?                      │   0 (unbuilt) │\n",
+       "│ (RandomRotation)                │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ random_flip (RandomFlip)        │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d (Conv2D)                 │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d (MaxPooling2D)    │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_1 (Conv2D)               │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_1 (MaxPooling2D)  │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_2 (Conv2D)               │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_2 (MaxPooling2D)  │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_3 (Conv2D)               │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_3 (MaxPooling2D)  │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten (Flatten)               │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (Dense)                   │ ?                      │   0 (unbuilt) │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (Dropout)               │ ?                      │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (Dense)                 │ ?                      │   0 (unbuilt) │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ random_zoom (\u001b[38;5;33mRandomZoom\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ random_rotation │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "│ (\u001b[38;5;33mRandomRotation\u001b[0m) │ │ │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ random_flip (\u001b[38;5;33mRandomFlip\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 0 (0.00 B)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 0 (0.00 B)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 0 (0.00 B)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "check_var_defined('model_dropout')\n", "model_dropout.summary()" ] }, + { + "cell_type": "code", + "execution_count": 32, + "id": "92ec2689", + "metadata": { + "deletable": false, + "nbgrader": { + "cell_type": "code", + "checksum": "c89d459ee4ecefb767369c54929ecfb0", + "grade": true, + "grade_id": "cell-82fcca9814ec3c0e", + "locked": false, + "points": 1, + "schema_version": 3, + "solution": true, + "task": false + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 258ms/step - categorical_accuracy: 0.2455 - loss: 1.6014 - val_categorical_accuracy: 0.2916 - val_loss: 1.5391\n", + "Epoch 2/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 264ms/step - categorical_accuracy: 0.3000 - loss: 1.5297 - val_categorical_accuracy: 0.3379 - val_loss: 1.4781\n", + "Epoch 3/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 254ms/step - categorical_accuracy: 0.3400 - loss: 1.4764 - val_categorical_accuracy: 0.3515 - val_loss: 1.4463\n", + "Epoch 4/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 254ms/step - categorical_accuracy: 0.3607 - loss: 1.4422 - val_categorical_accuracy: 0.4278 - val_loss: 1.3648\n", + "Epoch 5/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 256ms/step - categorical_accuracy: 0.3780 - loss: 1.3957 - val_categorical_accuracy: 0.4741 - val_loss: 1.3091\n", + "Epoch 6/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.4264 - loss: 1.3473 - val_categorical_accuracy: 0.5041 - val_loss: 1.2634\n", + "Epoch 7/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.4359 - loss: 1.3280 - val_categorical_accuracy: 0.4905 - val_loss: 1.2468\n", + "Epoch 8/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 255ms/step - categorical_accuracy: 0.4456 - loss: 1.3061 - val_categorical_accuracy: 0.5259 - val_loss: 1.2070\n", + "Epoch 9/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.4730 - loss: 1.2948 - val_categorical_accuracy: 0.5259 - val_loss: 1.1895\n", + "Epoch 10/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 254ms/step - categorical_accuracy: 0.4730 - loss: 1.2780 - val_categorical_accuracy: 0.5232 - val_loss: 1.1882\n", + "Epoch 11/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.4722 - loss: 1.2699 - val_categorical_accuracy: 0.5668 - val_loss: 1.1537\n", + "Epoch 12/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.5036 - loss: 1.2272 - val_categorical_accuracy: 0.5804 - val_loss: 1.1287\n", + "Epoch 13/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.5042 - loss: 1.2143 - val_categorical_accuracy: 0.5777 - val_loss: 1.1289\n", + "Epoch 14/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.5186 - loss: 1.2249 - val_categorical_accuracy: 0.5858 - val_loss: 1.1071\n", + "Epoch 15/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.5055 - loss: 1.1896 - val_categorical_accuracy: 0.5777 - val_loss: 1.1020\n", + "Epoch 16/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 252ms/step - categorical_accuracy: 0.5239 - loss: 1.1767 - val_categorical_accuracy: 0.5913 - val_loss: 1.0925\n", + "Epoch 17/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.5264 - loss: 1.1780 - val_categorical_accuracy: 0.5804 - val_loss: 1.0838\n", + "Epoch 18/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 258ms/step - categorical_accuracy: 0.5320 - loss: 1.1648 - val_categorical_accuracy: 0.5967 - val_loss: 1.0745\n", + "Epoch 19/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 253ms/step - categorical_accuracy: 0.5469 - loss: 1.1741 - val_categorical_accuracy: 0.5940 - val_loss: 1.0532\n", + "Epoch 20/20\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 254ms/step - categorical_accuracy: 0.5266 - loss: 1.1739 - val_categorical_accuracy: 0.5967 - val_loss: 1.0518\n" + ] + } + ], + "source": [ + "tf.keras.utils.set_random_seed(103745)\n", + "# YOUR CODE HERE\n", + "model_dropout.compile(loss=\"categorical_crossentropy\",\n", + " optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n", + " metrics=[tf.keras.metrics.CategoricalAccuracy()])\n", + "\n", + "history_dropout = model_dropout.fit(x_train, y_train, epochs=20,\n", + " validation_data=(x_val, y_val),\n", + " batch_size=32)\n", + "#raise NotImplementedError()" + ] + }, { "cell_type": "markdown", "id": "6778a133", @@ -1937,32 +2362,7 @@ }, { "cell_type": "code", - "execution_count": null, - "id": "92ec2689", - "metadata": { - "deletable": false, - "nbgrader": { - "cell_type": "code", - "checksum": "c89d459ee4ecefb767369c54929ecfb0", - "grade": true, - "grade_id": "cell-82fcca9814ec3c0e", - "locked": false, - "points": 1, - "schema_version": 3, - "solution": true, - "task": false - } - }, - "outputs": [], - "source": [ - "tf.keras.utils.set_random_seed(103745)\n", - "# YOUR CODE HERE\n", - "raise NotImplementedError()" - ] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 33, "id": "5048652c", "metadata": { "deletable": false, @@ -1979,14 +2379,22 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "history_dropout defined.\n" + ] + } + ], "source": [ "check_var_defined('history_dropout')" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "id": "128cc76b", "metadata": { "deletable": false, @@ -2002,7 +2410,28 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plot_metrics(history_dropout)" ] @@ -2046,7 +2475,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "While the accuracy is lower and the loss higher than the basic model despite more time training, we can see from the plots that the training and validation loss and accuracy diverge much more slowly. This suggests the model is less susceptible to overfitting, so we are likely to get a better model with more training." ] }, { @@ -2088,7 +2517,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Each epoch has less training data to work from, so the model takes longer to learn class features with the same learning rate." ] }, { @@ -2114,7 +2543,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 35, "id": "b5d2ea24", "metadata": { "deletable": false, @@ -2130,7 +2559,26 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step \n", + "Average Recall: 0.685, Average Precision 0.682\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "test_targets_dropout = model_predict(model_dropout, x_test)\n", "recall_dropout, precision_dropout = average_recall_precision(test_targets, test_targets_dropout) \n", @@ -2139,7 +2587,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 36, "id": "dbae38a3", "metadata": { "deletable": false, @@ -2156,7 +2604,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "test_targets_dropout defined.\n", + "recall_dropout defined.\n" + ] + } + ], "source": [ "check_var_defined('test_targets_dropout')\n", "check_var_defined('recall_dropout')" @@ -2164,7 +2621,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 37, "id": "98f7bbc4", "metadata": { "deletable": false, @@ -2181,7 +2638,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "test_targets_dropout defined.\n", + "precision_dropout defined.\n" + ] + } + ], "source": [ "check_var_defined('test_targets_dropout')\n", "check_var_defined('precision_dropout')" @@ -2226,7 +2692,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The model is more precise and has better recall than the previous model, as we can see by a lower proportion of misidentifications for example mistaking roses for tulips as before. However, the difference is not enormous - more training may yield better results." ] }, { @@ -2272,7 +2738,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "Transfer learning allows us to use a pre-trained model which saves time by using weights that have already been found and reduces overfitting as the model will be more general than our dataset. " ] }, { @@ -2298,7 +2764,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "id": "152fe58b", "metadata": { "deletable": false, @@ -2314,7 +2780,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Output shape of the MobileNet: (None, 7, 7, 1024)\n" + ] + } + ], "source": [ "mobilenet = tf.keras.applications.mobilenet.MobileNet(\n", " input_shape=(224, 224, 3),\n", @@ -2351,7 +2825,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 39, "id": "6427f088", "metadata": { "deletable": false, @@ -2373,12 +2847,21 @@ "tf.keras.utils.set_random_seed(387453)\n", "\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_mobilenet = tf.keras.models.Sequential([\n", + " mobilenet,\n", + " tf.keras.layers.MaxPool2D(strides=(2,2)),\n", + " tf.keras.layers.Flatten(),\n", + " tf.keras.layers.Dense(32, activation=\"relu\"),\n", + " tf.keras.layers.Dropout(0.5),\n", + " tf.keras.layers.Dense(5, activation=\"softmax\")\n", + "])\n", + "\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 40, "id": "27b1a82a", "metadata": { "deletable": false, @@ -2395,7 +2878,108 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model_mobilenet defined.\n" + ] + }, + { + "data": { + "text/html": [ + "
Model: \"sequential\"\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1mModel: \"sequential\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ mobilenet_1.00_224 (Functional) │ (None, 7, 7, 1024)     │     3,228,864 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d (MaxPooling2D)    │ (None, 3, 3, 1024)     │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten (Flatten)               │ (None, 9216)           │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (Dense)                   │ (None, 32)             │       294,944 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (Dropout)               │ (None, 32)             │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (Dense)                 │ (None, 5)              │           165 │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ mobilenet_1.00_224 (\u001b[38;5;33mFunctional\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m1024\u001b[0m) │ \u001b[38;5;34m3,228,864\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m1024\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m9216\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m294,944\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m) │ \u001b[38;5;34m165\u001b[0m │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 3,523,973 (13.44 MB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m3,523,973\u001b[0m (13.44 MB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 295,109 (1.13 MB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m295,109\u001b[0m (1.13 MB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 3,228,864 (12.32 MB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m3,228,864\u001b[0m (12.32 MB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "check_var_defined('model_mobilenet')\n", "model_mobilenet.summary()" @@ -2424,7 +3008,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 41, "id": "b06557e3", "metadata": { "deletable": false, @@ -2440,16 +3024,50 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 429ms/step - categorical_accuracy: 0.2296 - loss: 2.5558 - val_categorical_accuracy: 0.4741 - val_loss: 1.2791\n", + "Epoch 2/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 418ms/step - categorical_accuracy: 0.4566 - loss: 1.2256 - val_categorical_accuracy: 0.7193 - val_loss: 0.8473\n", + "Epoch 3/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 419ms/step - categorical_accuracy: 0.6146 - loss: 0.9444 - val_categorical_accuracy: 0.7956 - val_loss: 0.6352\n", + "Epoch 4/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m43s\u001b[0m 462ms/step - categorical_accuracy: 0.6761 - loss: 0.7756 - val_categorical_accuracy: 0.8501 - val_loss: 0.5471\n", + "Epoch 5/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 444ms/step - categorical_accuracy: 0.7207 - loss: 0.6936 - val_categorical_accuracy: 0.8365 - val_loss: 0.4774\n", + "Epoch 6/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 420ms/step - categorical_accuracy: 0.7470 - loss: 0.6032 - val_categorical_accuracy: 0.8638 - val_loss: 0.4606\n", + "Epoch 7/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 417ms/step - categorical_accuracy: 0.7697 - loss: 0.5277 - val_categorical_accuracy: 0.8665 - val_loss: 0.4382\n", + "Epoch 8/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 431ms/step - categorical_accuracy: 0.7939 - loss: 0.4792 - val_categorical_accuracy: 0.8828 - val_loss: 0.4102\n", + "Epoch 9/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 448ms/step - categorical_accuracy: 0.7955 - loss: 0.4710 - val_categorical_accuracy: 0.8747 - val_loss: 0.3781\n", + "Epoch 10/10\n", + "\u001b[1m92/92\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 438ms/step - categorical_accuracy: 0.7994 - loss: 0.4482 - val_categorical_accuracy: 0.8747 - val_loss: 0.3842\n" + ] + } + ], "source": [ "tf.keras.utils.set_random_seed(9673)\n", "# YOUR CODE HERE\n", - "raise NotImplementedError()" + "model_mobilenet.compile(loss=\"categorical_crossentropy\",\n", + " optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n", + " metrics=[tf.keras.metrics.CategoricalAccuracy()])\n", + "\n", + "history_mobilenet = model_mobilenet.fit(x_train, y_train, epochs=10,\n", + " validation_data=(x_val, y_val),\n", + " batch_size=32)\n", + "#raise NotImplementedError()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 42, "id": "6268f779", "metadata": { "deletable": false, @@ -2466,14 +3084,22 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "history_mobilenet defined.\n" + ] + } + ], "source": [ "check_var_defined('history_mobilenet')" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 43, "id": "6cbcc8b8", "metadata": { "deletable": false, @@ -2489,14 +3115,35 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plot_metrics(history_mobilenet)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 44, "id": "fd842596", "metadata": { "deletable": false, @@ -2512,7 +3159,26 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 414ms/step\n", + "Average Recall: 0.885, Average Precision 0.881\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "test_targets_mobilenet = model_predict(model_mobilenet, x_test)\n", "recall_mobilenet, precision_mobilenet = average_recall_precision(test_targets, test_targets_mobilenet) \n", @@ -2521,7 +3187,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 45, "id": "e2342a8b", "metadata": { "deletable": false, @@ -2538,7 +3204,16 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "test_targets_mobilenet defined.\n", + "recall_mobilenet defined.\n" + ] + } + ], "source": [ "check_var_defined('test_targets_mobilenet')\n", "check_var_defined('recall_mobilenet')\n" @@ -2546,7 +3221,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 46, "id": "2bb96e04", "metadata": { "deletable": false, @@ -2563,7 +3238,15 @@ "task": false } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "precision_mobilenet defined.\n" + ] + } + ], "source": [ "check_var_defined('precision_mobilenet')\n" ] @@ -2607,7 +3290,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "The initial accuracy started lower and the loss higher than with the other models. However, the transfer model was able to learn much more quickly and overtook the other models within a few generations. The average precision and recall are significantly better, and it can be seen from the confusion matrix that there was a much lower proportion of misclassification, with the model being very good at positive classification." ] }, { @@ -2649,7 +3332,7 @@ } }, "source": [ - "YOUR ANSWER HERE" + "As always, more training data and more tranining time would improve the results. Learning reate scheduling to reduce the learning rate during training could allow for faster convergence of the model. Different optimisation functions from Adam could also improve results. A deeper model architecture could allow for more nuanced features to be learned." ] } ],