2019-06-10 17:00:28 +00:00
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"pycharm": {
2019-06-16 21:59:07 +00:00
"name": "#%%\n"
2019-06-10 17:00:28 +00:00
}
},
"outputs": [
{
2019-06-16 21:59:07 +00:00
"name": "stderr",
2019-06-10 17:00:28 +00:00
"output_type": "stream",
"text": [
2019-06-16 21:59:07 +00:00
"/usr/local/lib/python3.5/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.\n",
" from ._conv import register_converters as _register_converters\n",
"Using TensorFlow backend.\n"
2019-06-10 17:00:28 +00:00
]
}
],
"source": [
2019-06-16 21:59:07 +00:00
"# Trains - Example of integrating plots and training on jupyter notebook. \n",
"# In this example, simple graphs are shown, then an MNIST classifier is trained using Keras.\n",
"\n",
"from keras.callbacks import TensorBoard, ModelCheckpoint\n",
"from keras.datasets import mnist\n",
"from keras.models import Sequential\n",
"from keras.layers.core import Dense, Dropout, Activation\n",
"from keras.optimizers import SGD, Adam, RMSprop\n",
"from keras.utils import np_utils\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n"
2019-06-10 17:00:28 +00:00
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
2019-06-16 21:59:07 +00:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"TRAINS Task: overwriting (reusing) task id=8d23de406d0a4159a496b64c7eba0e32\n",
"======> WARNING! UNCOMMITTED CHANGES IN REPOSITORY https://github.com/allegroai/trains.git <======\n",
"TRAINS results page: https://demoapp.trainsai.io/projects/087f765c846c4c76a7e9f3d035667d82/experiments/8d23de406d0a4159a496b64c7eba0e32/output/log\n"
]
}
],
2019-06-10 17:00:28 +00:00
"source": [
2019-06-16 21:59:07 +00:00
"# Connecting TRAINS\n",
"from trains import Task\n",
"task = Task.init(project_name = 'examples', task_name = 'notebook example')\n"
2019-06-10 17:00:28 +00:00
]
},
{
"cell_type": "code",
2019-06-16 21:59:07 +00:00
"execution_count": 4,
2019-06-10 17:00:28 +00:00
"metadata": {
2019-06-16 21:59:07 +00:00
"scrolled": true
2019-06-10 17:00:28 +00:00
},
2019-06-16 21:59:07 +00:00
"outputs": [],
"source": [
"# Set script parameters\n",
"task_params = {'num_scatter_samples': 60, 'sin_max_value': 20, 'sin_steps': 30}\n",
"task_params = task.connect(task_params)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Simple plots. You can view the plots in experiments results page "
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
2019-06-10 17:00:28 +00:00
"outputs": [
{
"data": {
2019-06-16 21:59:07 +00:00
"image/png": "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
2019-06-10 17:00:28 +00:00
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
2019-06-16 21:59:07 +00:00
"image/png": "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
2019-06-10 17:00:28 +00:00
"text/plain": [
2019-06-16 21:59:07 +00:00
"<Figure size 432x288 with 1 Axes>"
2019-06-10 17:00:28 +00:00
]
},
2019-06-16 21:59:07 +00:00
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
2019-06-10 17:00:28 +00:00
},
{
"data": {
2019-06-16 21:59:07 +00:00
"image/png": "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
2019-06-10 17:00:28 +00:00
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
2019-06-16 21:59:07 +00:00
"%matplotlib inline\n",
"N = task_params['num_scatter_samples']\n",
2019-06-10 17:00:28 +00:00
"x = np.random.rand(N)\n",
"y = np.random.rand(N)\n",
"colors = np.random.rand(N)\n",
2019-06-16 21:59:07 +00:00
"area = (50 * np.random.rand(N))**2 # 0 to 15 point radii\n",
2019-06-10 17:00:28 +00:00
"plt.scatter(x, y, s=area, c=colors, alpha=0.5)\n",
2019-06-16 21:59:07 +00:00
"plt.title('Nice Circles')\n",
2019-06-10 17:00:28 +00:00
"plt.show()\n",
"\n",
2019-06-16 21:59:07 +00:00
"x = np.linspace(0, task_params['sin_max_value'], task_params['sin_steps'])\n",
2019-06-10 17:00:28 +00:00
"y = np.sin(x)\n",
2019-06-16 21:59:07 +00:00
"plt.plot(x, y, 'o', color='black')\n",
"plt.title('Sinus Dots')\n",
"plt.show()\n",
"\n",
"m = np.eye(32, 32, dtype=np.uint8)\n",
"plt.imshow(m)\n",
"plt.title('sample output')\n",
"plt.show()"
2019-06-10 17:00:28 +00:00
]
},
{
2019-06-16 21:59:07 +00:00
"cell_type": "markdown",
2019-06-10 17:00:28 +00:00
"metadata": {},
2019-06-16 21:59:07 +00:00
"source": [
"Keras training example\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"# Notice, Updating task_params is traced and updated in TRAINS\n",
"task_params['batch_size'] = 128\n",
"task_params['nb_classes'] = 10\n",
"task_params['nb_epoch'] = 6\n",
"task_params['hidden_dim'] = 512\n",
"batch_size = task_params['batch_size']\n",
"nb_classes = task_params['nb_classes']\n",
"nb_epoch = task_params['nb_epoch']\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
2019-06-10 17:00:28 +00:00
"outputs": [
{
2019-06-16 21:59:07 +00:00
"name": "stdout",
"output_type": "stream",
"text": [
"60000 train samples\n",
"10000 test samples\n",
"WARNING:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Colocations handled automatically by placer.\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"dense_1 (Dense) (None, 512) 401920 \n",
"_________________________________________________________________\n",
"activation_1 (Activation) (None, 512) 0 \n",
"_________________________________________________________________\n",
"dense_2 (Dense) (None, 512) 262656 \n",
"_________________________________________________________________\n",
"activation_2 (Activation) (None, 512) 0 \n",
"_________________________________________________________________\n",
"dense_3 (Dense) (None, 10) 5130 \n",
"_________________________________________________________________\n",
"activation_3 (Activation) (None, 10) 0 \n",
"=================================================================\n",
"Total params: 669,706\n",
"Trainable params: 669,706\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n",
"WARNING:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use tf.cast instead.\n",
"Train on 60000 samples, validate on 10000 samples\n",
"Epoch 1/6\n",
"60000/60000 [==============================] - 4s 64us/step - loss: 0.2129 - acc: 0.9350 - val_loss: 0.1012 - val_acc: 0.9682\n",
"Epoch 2/6\n",
"60000/60000 [==============================] - 4s 68us/step - loss: 0.0813 - acc: 0.9752 - val_loss: 0.0684 - val_acc: 0.9779\n",
"Epoch 3/6\n",
"60000/60000 [==============================] - 4s 62us/step - loss: 0.0540 - acc: 0.9830 - val_loss: 0.0736 - val_acc: 0.9793\n",
"Epoch 4/6\n",
"60000/60000 [==============================] - 4s 64us/step - loss: 0.0387 - acc: 0.9880 - val_loss: 0.0859 - val_acc: 0.9761\n",
"Epoch 5/6\n",
"60000/60000 [==============================] - 4s 63us/step - loss: 0.0304 - acc: 0.9904 - val_loss: 0.0875 - val_acc: 0.9766\n",
"Epoch 6/6\n",
"60000/60000 [==============================] - 4s 64us/step - loss: 0.0220 - acc: 0.9933 - val_loss: 0.0847 - val_acc: 0.9793\n",
"Test score: 0.08471047468512916\n",
"Test accuracy: 0.9793\n"
]
2019-06-10 17:00:28 +00:00
}
],
"source": [
2019-06-16 21:59:07 +00:00
"# the data, shuffled and split between train and test sets\n",
"(X_train, y_train), (X_test, y_test) = mnist.load_data()\n",
"\n",
"X_train = X_train.reshape(60000, 784)\n",
"X_test = X_test.reshape(10000, 784)\n",
"X_train = X_train.astype('float32')\n",
"X_test = X_test.astype('float32')\n",
"X_train /= 255.\n",
"X_test /= 255.\n",
"print(X_train.shape[0], 'train samples')\n",
"print(X_test.shape[0], 'test samples')\n",
"\n",
"# convert class vectors to binary class matrices\n",
"Y_train = np_utils.to_categorical(y_train, nb_classes)\n",
"Y_test = np_utils.to_categorical(y_test, nb_classes)\n",
"\n",
"hidden_dim = task_params['hidden_dim']\n",
"model = Sequential()\n",
"model.add(Dense(hidden_dim, input_shape=(784,)))\n",
"model.add(Activation('relu'))\n",
"# model.add(Dropout(0.2))\n",
"model.add(Dense(hidden_dim))\n",
"model.add(Activation('relu'))\n",
"# model.add(Dropout(0.2))\n",
"model.add(Dense(10))\n",
"model.add(Activation('softmax'))\n",
"\n",
"model.summary()\n",
"\n",
"model.compile(loss='categorical_crossentropy',\n",
" optimizer=RMSprop(),\n",
" metrics=['accuracy'])\n",
"\n",
"board = TensorBoard(histogram_freq=1, log_dir='/tmp/histogram_example')\n",
"model_store = ModelCheckpoint(filepath='/tmp/weight.{epoch}.hdf5')\n",
"\n",
"model.fit(X_train, Y_train,\n",
" batch_size=batch_size, epochs=nb_epoch,\n",
" callbacks=[board, model_store],\n",
" verbose=1, validation_data=(X_test, Y_test))\n",
"score = model.evaluate(X_test, Y_test, verbose=0)\n",
"print('Test score:', score[0])\n",
"print('Test accuracy:', score[1])\n"
2019-06-10 17:00:28 +00:00
]
}
],
"metadata": {
"kernelspec": {
2019-06-16 21:59:07 +00:00
"display_name": "Python 3",
2019-06-10 17:00:28 +00:00
"language": "python",
2019-06-16 21:59:07 +00:00
"name": "python3"
2019-06-10 17:00:28 +00:00
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
},
"pycharm": {
"stem_cell": {
"cell_type": "raw",
"metadata": {
"collapsed": false
},
"source": []
}
}
},
"nbformat": 4,
2019-06-16 21:59:07 +00:00
"nbformat_minor": 2
2019-06-10 17:00:28 +00:00
}
