Last active
July 13, 2017 07:29
Star
You must be signed in to star a gist
MNIST example with Keras model and TF ops
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import tensorflow as tf | |
from tensorflow.contrib.keras.api import keras | |
from tensorflow.contrib.keras.api.keras.models import Model, load_model | |
from tensorflow.contrib.keras.api.keras.layers import Input, Dense, Dropout, Flatten, Conv2D, MaxPooling2D, Activation, Lambda | |
from tensorflow.contrib.keras.api.keras.datasets import mnist | |
from tensorflow.contrib.keras.api.keras.utils import to_categorical | |
import numpy as np | |
import matplotlib.pyplot as plt | |
import argparse | |
def get_session(): | |
config = tf.ConfigProto() | |
config.gpu_options.allow_growth = True | |
return tf.Session(config=config) | |
def weight_variable(shape): | |
initial = tf.truncated_normal(shape, stddev=0.1) | |
return tf.Variable(initial) | |
def bias_variable(shape): | |
initial = tf.constant(0.1, shape=shape) | |
return tf.Variable(initial) | |
def conv2d(x, W): | |
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') | |
def max_pool_2x2(x): | |
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') | |
def create_model(num_classes): | |
inputs = Input(shape=(28, 28, 1)) | |
W_conv1 = weight_variable([3, 3, 1, 32]) | |
b_conv1 = bias_variable([32]) | |
W_conv2 = weight_variable([3, 3, 32, 64]) | |
b_conv2 = bias_variable([64]) | |
W_fc1 = weight_variable([14 * 14 * 64, 128]) | |
b_fc1 = bias_variable([128]) | |
W_fc2 = weight_variable([128, 10]) | |
b_fc2 = bias_variable([10]) | |
x = Lambda(lambda x: tf.nn.relu(conv2d(x, W_conv1) + b_conv1))(inputs) | |
x = Lambda(lambda x: max_pool_2x2(tf.nn.relu(conv2d(x, W_conv2) + b_conv2)))(x) | |
x = Dropout(0.25)(x) | |
x = Flatten()(x) | |
x = Lambda(lambda x: tf.nn.relu(tf.matmul(x, W_fc1) + b_fc1))(x) | |
x = Dropout(0.5)(x) | |
x = Lambda(lambda x: tf.matmul(x, W_fc2) + b_fc2)(x) | |
predictions = Activation('softmax')(x) | |
model = Model(inputs=inputs, outputs=predictions) | |
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) | |
print(model.summary()) | |
return model | |
def parse_args(): | |
parser = argparse.ArgumentParser(description='MNIST Training.') | |
parser.add_argument('--model', help='Model to use to resume training.') | |
parser.add_argument('--no-train', help='Disables training, only evaluate.', dest='no_train', action='store_true') | |
parser.add_argument('--num-classes', help='Number of classes.', default=10) | |
parser.add_argument('--seed', help='Random seed to use.', default=1) | |
parser.add_argument('--batch-size', help='Size of the batch.', default=128) | |
parser.add_argument('--epochs', help='Number of epochs to run.', default=4) | |
parser.add_argument('--target', help='Target file for the resulting model.', default='mnist.h5') | |
parser.set_defaults(no_train=False) | |
return parser.parse_args() | |
if __name__=='__main__': | |
args = parse_args() | |
np.random.seed(args.seed) | |
keras.backend.set_session(get_session()) | |
# load and preprocess data | |
(X_train, y_train), (X_test, y_test) = mnist.load_data() | |
X_train = X_train.reshape(-1, 28, 28, 1).astype(np.float32) / 255 | |
X_test = X_test.reshape(-1, 28, 28, 1).astype(np.float32) / 255 | |
y_train = to_categorical(y_train, args.num_classes) | |
y_test = to_categorical(y_test, args.num_classes) | |
if args.model: | |
print('Loading model from {}'.format(args.model)) | |
model = load_model(args.model) | |
else: | |
# create model | |
model = create_model(args.num_classes) | |
if not args.no_train: | |
# fit model | |
model.fit( | |
X_train, | |
y_train, | |
batch_size=args.batch_size, | |
epochs=args.epochs, | |
shuffle=True, | |
verbose=1, | |
validation_data=(X_test, y_test) | |
) | |
# save model | |
model.save(args.target) | |
# evaluate model | |
score = model.evaluate(X_test, y_test, verbose=0) | |
print('Test loss: {}'.format(score[0])) | |
print('Test accuracy: {}'.format(score[1])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment