{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# High-level RNN Keras (CNTK) Example"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using CNTK backend\n"
]
}
],
"source": [
"import os\n",
"import sys\n",
"import numpy as np\n",
"os.environ['KERAS_BACKEND'] = \"cntk\"\n",
"import keras as K\n",
"import cntk\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense, Embedding, GRU, CuDNNGRU\n",
"from common.params_lstm import *\n",
"from common.utils import *"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"OS: linux\n",
"Python: 3.5.2 |Anaconda custom (64-bit)| (default, Jul 2 2016, 17:53:06) \n",
"[GCC 4.4.7 20120313 (Red Hat 4.4.7-1)]\n",
"Keras: 2.1.1\n",
"Numpy: 1.13.3\n",
"CNTK: 2.2\n",
"cntk\n"
]
}
],
"source": [
"print(\"OS: \", sys.platform)\n",
"print(\"Python: \", sys.version)\n",
"print(\"Keras: \", K.__version__)\n",
"print(\"Numpy: \", np.__version__)\n",
"print(\"CNTK: \", cntk.__version__)\n",
"print(K.backend.backend())"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def create_symbol(CUDNN=True):\n",
" model = Sequential()\n",
" model.add(Embedding(MAXFEATURES, EMBEDSIZE, input_length=MAXLEN))\n",
" # Only return last output\n",
" if not CUDNN:\n",
" model.add(GRU(NUMHIDDEN, return_sequences=False, return_state=False))\n",
" else:\n",
" model.add(CuDNNGRU(NUMHIDDEN, return_sequences=False, return_state=False))\n",
" model.add(Dense(2, activation='softmax'))\n",
" return model"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def init_model(m):\n",
" m.compile(\n",
" loss = \"categorical_crossentropy\",\n",
" optimizer = K.optimizers.Adam(LR, BETA_1, BETA_2, EPS),\n",
" metrics = ['accuracy'])\n",
" return m"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Preparing train set...\n",
"Preparing test set...\n",
"Trimming to 30000 max-features\n",
"Padding to length 150\n",
"(25000, 150) (25000, 150) (25000, 2) (25000, 2)\n",
"int32 int32 int32 int32\n",
"CPU times: user 5.3 s, sys: 278 ms, total: 5.58 s\n",
"Wall time: 5.58 s\n"
]
}
],
"source": [
"%%time\n",
"# Data into format for library\n",
"x_train, x_test, y_train, y_test = imdb_for_library(seq_len=MAXLEN, max_features=MAXFEATURES, one_hot=True)\n",
"print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)\n",
"print(x_train.dtype, x_test.dtype, y_train.dtype, y_test.dtype)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 137 ms, sys: 107 ms, total: 244 ms\n",
"Wall time: 111 ms\n"
]
}
],
"source": [
"%%time\n",
"# Load symbol\n",
"# CuDNN RNNs are only available with the TensorFlow backend.\n",
"sym = create_symbol(CUDNN=False)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 7.83 ms, sys: 0 ns, total: 7.83 ms\n",
"Wall time: 7.8 ms\n"
]
}
],
"source": [
"%%time\n",
"# Initialise model\n",
"model = init_model(sym)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"embedding_2 (Embedding) (None, 150, 125) 3750000 \n",
"_________________________________________________________________\n",
"gru_1 (GRU) (None, 100) 67800 \n",
"_________________________________________________________________\n",
"dense_1 (Dense) (None, 2) 202 \n",
"=================================================================\n",
"Total params: 3,818,002\n",
"Trainable params: 3,818,002\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"model.summary()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/3\n",
"25000/25000 [==============================] - 29s 1ms/step - loss: 0.4392 - acc: 0.7803\n",
"Epoch 2/3\n",
"25000/25000 [==============================] - 29s 1ms/step - loss: 0.2057 - acc: 0.9239\n",
"Epoch 3/3\n",
"25000/25000 [==============================] - 29s 1ms/step - loss: 0.1104 - acc: 0.9631\n",
"CPU times: user 1min 23s, sys: 3.78 s, total: 1min 27s\n",
"Wall time: 1min 26s\n"
]
},
{
"data": {
"text/plain": [
"<keras.callbacks.History at 0x7f33482c9550>"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%time\n",
"# 86s\n",
"# Train model\n",
"model.fit(x_train,\n",
" y_train,\n",
" batch_size=BATCHSIZE,\n",
" epochs=EPOCHS,\n",
" verbose=1)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 10.2 s, sys: 236 ms, total: 10.4 s\n",
"Wall time: 10.4 s\n"
]
}
],
"source": [
"%%time\n",
"y_guess = model.predict(x_test, batch_size=BATCHSIZE)\n",
"y_guess = np.argmax(y_guess, axis=-1)\n",
"y_truth = np.argmax(y_test, axis=-1)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.86092\n"
]
}
],
"source": [
"print(\"Accuracy: \", sum(y_guess == y_truth)/len(y_guess))"
]
}
],
"metadata": {
"anaconda-cloud": {},
"kernelspec": {
"display_name": "Python [default]",
"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": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}