mirror of
https://github.com/donnemartin/data-science-ipython-notebooks.git
synced 2024-03-22 13:30:56 +08:00
324 lines
8.5 KiB
Python
324 lines
8.5 KiB
Python
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "kR-4eNdK6lYS"
|
|
},
|
|
"source": [
|
|
"Deep Learning with TensorFlow\n",
|
|
"=============\n",
|
|
"\n",
|
|
"Credits: Forked from [TensorFlow](https://github.com/tensorflow/tensorflow) by Google\n",
|
|
"\n",
|
|
"Setup\n",
|
|
"------------\n",
|
|
"\n",
|
|
"Refer to the [setup instructions](https://github.com/donnemartin/data-science-ipython-notebooks/tree/feature/deep-learning/deep-learning/tensor-flow-exercises/README.md).\n",
|
|
"\n",
|
|
"Exercise 3\n",
|
|
"------------\n",
|
|
"\n",
|
|
"Previously in `2_fullyconnected.ipynb`, you trained a logistic regression and a neural network model.\n",
|
|
"\n",
|
|
"The goal of this exercise is to explore regularization techniques."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"cellView": "both",
|
|
"colab": {
|
|
"autoexec": {
|
|
"startup": false,
|
|
"wait_interval": 0
|
|
}
|
|
},
|
|
"colab_type": "code",
|
|
"collapsed": true,
|
|
"id": "JLpLa8Jt7Vu4"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# These are all the modules we'll be using later. Make sure you can import them\n",
|
|
"# before proceeding further.\n",
|
|
"import cPickle as pickle\n",
|
|
"import numpy as np\n",
|
|
"import tensorflow as tf"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "1HrCK6e17WzV"
|
|
},
|
|
"source": [
|
|
"First reload the data we generated in _notmist.ipynb_."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"cellView": "both",
|
|
"colab": {
|
|
"autoexec": {
|
|
"startup": false,
|
|
"wait_interval": 0
|
|
},
|
|
"output_extras": [
|
|
{
|
|
"item_id": 1
|
|
}
|
|
]
|
|
},
|
|
"colab_type": "code",
|
|
"collapsed": false,
|
|
"executionInfo": {
|
|
"elapsed": 11777,
|
|
"status": "ok",
|
|
"timestamp": 1449849322348,
|
|
"user": {
|
|
"color": "",
|
|
"displayName": "",
|
|
"isAnonymous": false,
|
|
"isMe": true,
|
|
"permissionId": "",
|
|
"photoUrl": "",
|
|
"sessionId": "0",
|
|
"userId": ""
|
|
},
|
|
"user_tz": 480
|
|
},
|
|
"id": "y3-cj1bpmuxc",
|
|
"outputId": "e03576f1-ebbe-4838-c388-f1777bcc9873"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Training set (200000, 28, 28) (200000,)\n",
|
|
"Validation set (10000, 28, 28) (10000,)\n",
|
|
"Test set (18724, 28, 28) (18724,)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"pickle_file = 'notMNIST.pickle'\n",
|
|
"\n",
|
|
"with open(pickle_file, 'rb') as f:\n",
|
|
" save = pickle.load(f)\n",
|
|
" train_dataset = save['train_dataset']\n",
|
|
" train_labels = save['train_labels']\n",
|
|
" valid_dataset = save['valid_dataset']\n",
|
|
" valid_labels = save['valid_labels']\n",
|
|
" test_dataset = save['test_dataset']\n",
|
|
" test_labels = save['test_labels']\n",
|
|
" del save # hint to help gc free up memory\n",
|
|
" print 'Training set', train_dataset.shape, train_labels.shape\n",
|
|
" print 'Validation set', valid_dataset.shape, valid_labels.shape\n",
|
|
" print 'Test set', test_dataset.shape, test_labels.shape"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "L7aHrm6nGDMB"
|
|
},
|
|
"source": [
|
|
"Reformat into a shape that's more adapted to the models we're going to train:\n",
|
|
"- data as a flat matrix,\n",
|
|
"- labels as float 1-hot encodings."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"cellView": "both",
|
|
"colab": {
|
|
"autoexec": {
|
|
"startup": false,
|
|
"wait_interval": 0
|
|
},
|
|
"output_extras": [
|
|
{
|
|
"item_id": 1
|
|
}
|
|
]
|
|
},
|
|
"colab_type": "code",
|
|
"collapsed": false,
|
|
"executionInfo": {
|
|
"elapsed": 11728,
|
|
"status": "ok",
|
|
"timestamp": 1449849322356,
|
|
"user": {
|
|
"color": "",
|
|
"displayName": "",
|
|
"isAnonymous": false,
|
|
"isMe": true,
|
|
"permissionId": "",
|
|
"photoUrl": "",
|
|
"sessionId": "0",
|
|
"userId": ""
|
|
},
|
|
"user_tz": 480
|
|
},
|
|
"id": "IRSyYiIIGIzS",
|
|
"outputId": "3f8996ee-3574-4f44-c953-5c8a04636582"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Training set (200000, 784) (200000, 10)\n",
|
|
"Validation set (10000, 784) (10000, 10)\n",
|
|
"Test set (18724, 784) (18724, 10)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"image_size = 28\n",
|
|
"num_labels = 10\n",
|
|
"\n",
|
|
"def reformat(dataset, labels):\n",
|
|
" dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32)\n",
|
|
" # Map 2 to [0.0, 1.0, 0.0 ...], 3 to [0.0, 0.0, 1.0 ...]\n",
|
|
" labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)\n",
|
|
" return dataset, labels\n",
|
|
"train_dataset, train_labels = reformat(train_dataset, train_labels)\n",
|
|
"valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)\n",
|
|
"test_dataset, test_labels = reformat(test_dataset, test_labels)\n",
|
|
"print 'Training set', train_dataset.shape, train_labels.shape\n",
|
|
"print 'Validation set', valid_dataset.shape, valid_labels.shape\n",
|
|
"print 'Test set', test_dataset.shape, test_labels.shape"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"cellView": "both",
|
|
"colab": {
|
|
"autoexec": {
|
|
"startup": false,
|
|
"wait_interval": 0
|
|
}
|
|
},
|
|
"colab_type": "code",
|
|
"collapsed": true,
|
|
"id": "RajPLaL_ZW6w"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"def accuracy(predictions, labels):\n",
|
|
" return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))\n",
|
|
" / predictions.shape[0])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "sgLbUAQ1CW-1"
|
|
},
|
|
"source": [
|
|
"---\n",
|
|
"Problem 1\n",
|
|
"---------\n",
|
|
"\n",
|
|
"Introduce and tune L2 regularization for both logistic and neural network models. Remember that L2 amounts to adding a penalty on the norm of the weights to the loss. In TensorFlow, you can compue the L2 loss for a tensor `t` using `nn.l2_loss(t)`. The right amount of regularization should improve your validation / test accuracy.\n",
|
|
"\n",
|
|
"---"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "na8xX2yHZzNF"
|
|
},
|
|
"source": [
|
|
"---\n",
|
|
"Problem 2\n",
|
|
"---------\n",
|
|
"Let's demonstrate an extreme case of overfitting. Restrict your training data to just a few batches. What happens?\n",
|
|
"\n",
|
|
"---"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "ww3SCBUdlkRc"
|
|
},
|
|
"source": [
|
|
"---\n",
|
|
"Problem 3\n",
|
|
"---------\n",
|
|
"Introduce Dropout on the hidden layer of the neural network. Remember: Dropout should only be introduced during training, not evaluation, otherwise your evaluation results would be stochastic as well. TensorFlow provides `nn.dropout()` for that, but you have to make sure it's only inserted during training.\n",
|
|
"\n",
|
|
"What happens to our extreme overfitting case?\n",
|
|
"\n",
|
|
"---"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "-b1hTz3VWZjw"
|
|
},
|
|
"source": [
|
|
"---\n",
|
|
"Problem 4\n",
|
|
"---------\n",
|
|
"\n",
|
|
"Try to get the best performance you can using a multi-layer model! The best reported test accuracy using a deep network is [97.1%](http://yaroslavvb.blogspot.com/2011/09/notmnist-dataset.html?showComment=1391023266211#c8758720086795711595).\n",
|
|
"\n",
|
|
"One avenue you can explore is to add multiple layers.\n",
|
|
"\n",
|
|
"Another one is to use learning rate decay:\n",
|
|
"\n",
|
|
" global_step = tf.Variable(0) # count the number of steps taken.\n",
|
|
" learning_rate = tf.train.exponential_decay(0.5, step, ...)\n",
|
|
" optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)\n",
|
|
" \n",
|
|
" ---\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"colabVersion": "0.3.2",
|
|
"colab_default_view": {},
|
|
"colab_views": {},
|
|
"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": "3.4.3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0
|
|
}
|