167 lines
11 KiB
Plaintext
167 lines
11 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "iQjHqsmTAVLU"
|
|
},
|
|
"source": [
|
|
"## Exercise 3\n",
|
|
"In the videos you looked at how you would improve Fashion MNIST using Convolutions. For your exercise see if you can improve MNIST to 99.8% accuracy or more using only a single convolutional layer and a single MaxPooling 2D. You should stop training once the accuracy goes above this amount. It should happen in less than 20 epochs, so it's ok to hard code the number of epochs for training, but your training must end once it hits the above metric. If it doesn't, then you'll need to redesign your layers.\n",
|
|
"\n",
|
|
"I've started the code for you -- you need to finish it!\n",
|
|
"\n",
|
|
"When 99.8% accuracy has been hit, you should print out the string \"Reached 99.8% accuracy so cancelling training!\"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import tensorflow as tf\n",
|
|
"from os import path, getcwd, chdir\n",
|
|
"\n",
|
|
"# DO NOT CHANGE THE LINE BELOW. If you are developing in a local\n",
|
|
"# environment, then grab mnist.npz from the Coursera Jupyter Notebook\n",
|
|
"# and place it inside a local folder and edit the path to that location\n",
|
|
"path = f\"{getcwd()}/../tmp2/mnist.npz\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"config = tf.ConfigProto()\n",
|
|
"config.gpu_options.allow_growth = True\n",
|
|
"sess = tf.Session(config=config)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# GRADED FUNCTION: train_mnist_conv\n",
|
|
"def train_mnist_conv():\n",
|
|
" # Please write your code only where you are indicated.\n",
|
|
" # please do not remove model fitting inline comments.\n",
|
|
"\n",
|
|
" # Setup callback to stop when we hit 99.8% accuracy\n",
|
|
" class myCallback(tf.keras.callbacks.Callback):\n",
|
|
" def on_epoch_end(self, epoch, logs={}):\n",
|
|
" if (logs.get('acc')>0.998):\n",
|
|
" print(\"Reached 99.8% accuracy so cancelling training!\")\n",
|
|
" self.model.stop_training=True\n",
|
|
" \n",
|
|
" callbacks=myCallback()\n",
|
|
"\n",
|
|
" mnist = tf.keras.datasets.mnist\n",
|
|
" (training_images, training_labels), (test_images, test_labels) = mnist.load_data(path=path)\n",
|
|
" # Format inputs to be 4D vectors and normalizing \n",
|
|
" training_images = training_images.reshape(60000, 28, 28, 1)\n",
|
|
" training_images = training_images / 255.0\n",
|
|
" test_images = test_images.reshape(10000, 28, 28, 1)\n",
|
|
" test_images = test_images / 255.0\n",
|
|
"\n",
|
|
" model = tf.keras.models.Sequential([\n",
|
|
" # Add a couple layers of convolution and a single layer of pooling\n",
|
|
" # Only one layer of pooling due to such a high goal for accuracy\n",
|
|
" tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(28,28,1)),\n",
|
|
" tf.keras.layers.MaxPooling2D(3,3),\n",
|
|
" tf.keras.layers.Conv2D(64, (3,3), activation='relu'),\n",
|
|
" \n",
|
|
" # Flatten out input data\n",
|
|
" tf.keras.layers.Flatten(),\n",
|
|
" \n",
|
|
" # Add two hidden layers of size 128 to provide complexity needed to reach goal accuracy\n",
|
|
" tf.keras.layers.Dense(128, activation='relu'),\n",
|
|
" tf.keras.layers.Dense(128, activation='relu'),\n",
|
|
" tf.keras.layers.Dense(10, activation='softmax')\n",
|
|
" ])\n",
|
|
"\n",
|
|
" model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
|
|
" # model fitting\n",
|
|
" history = model.fit(\n",
|
|
" training_images, training_labels, epochs=20, callbacks=[callbacks]\n",
|
|
" )\n",
|
|
" # model fitting\n",
|
|
" return history.epoch, history.history['acc'][-1]\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Epoch 1/20\n",
|
|
"11104/60000 [====>.........................] - ETA: 17s - loss: 0.3921 - acc: 0.8788"
|
|
]
|
|
},
|
|
{
|
|
"ename": "KeyboardInterrupt",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
|
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
|
"\u001b[0;32m<ipython-input-8-1ff3c304aec3>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_mnist_conv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
|
|
"\u001b[0;32m<ipython-input-7-0b6012c60224>\u001b[0m in \u001b[0;36mtrain_mnist_conv\u001b[0;34m()\u001b[0m\n\u001b[1;32m 40\u001b[0m \u001b[0;31m# model fitting\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 41\u001b[0m history = model.fit(\n\u001b[0;32m---> 42\u001b[0;31m \u001b[0mtraining_images\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtraining_labels\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 43\u001b[0m )\n\u001b[1;32m 44\u001b[0m \u001b[0;31m# model fitting\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)\u001b[0m\n\u001b[1;32m 778\u001b[0m \u001b[0mvalidation_steps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvalidation_steps\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 779\u001b[0m \u001b[0mvalidation_freq\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvalidation_freq\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 780\u001b[0;31m steps_name='steps_per_epoch')\n\u001b[0m\u001b[1;32m 781\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 782\u001b[0m def evaluate(self,\n",
|
|
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training_arrays.py\u001b[0m in \u001b[0;36mmodel_iteration\u001b[0;34m(model, inputs, targets, sample_weights, batch_size, epochs, verbose, callbacks, val_inputs, val_targets, val_sample_weights, shuffle, initial_epoch, steps_per_epoch, validation_steps, validation_freq, mode, validation_in_fit, prepared_feed_values_from_dataset, steps_name, **kwargs)\u001b[0m\n\u001b[1;32m 361\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 362\u001b[0m \u001b[0;31m# Get outputs.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 363\u001b[0;31m \u001b[0mbatch_outs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mins_batch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 364\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch_outs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 365\u001b[0m \u001b[0mbatch_outs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mbatch_outs\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m 3290\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3291\u001b[0m fetched = self._callable_fn(*array_vals,\n\u001b[0;32m-> 3292\u001b[0;31m run_metadata=self.run_metadata)\n\u001b[0m\u001b[1;32m 3293\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_fetch_callbacks\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfetched\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_fetches\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3294\u001b[0m output_structure = nest.pack_sequence_as(\n",
|
|
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1456\u001b[0m ret = tf_session.TF_SessionRunCallable(self._session._session,\n\u001b[1;32m 1457\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_handle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1458\u001b[0;31m run_metadata_ptr)\n\u001b[0m\u001b[1;32m 1459\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1460\u001b[0m \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"_, _ = train_mnist_conv()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"coursera": {
|
|
"course_slug": "introduction-tensorflow",
|
|
"graded_item_id": "ml06H",
|
|
"launcher_item_id": "hQF8A"
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.6.8"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 1
|
|
}
|