教程 | 从基本概念到实现，全卷积网络实现更简洁的图像识别

from __future__ import print_function
import tensorflow as tf
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dropout, Activation, Convolution2D, GlobalAveragePooling2D
from keras.utils import np_utils
from keras.optimizers import SGD
from keras import backend as K
from keras.models import Model
from keras.layers.core import Lambda
from keras.callbacks import ModelCheckpoint
import pandas

def make_parallel(model, gpu_count):
    def get_slice(data, idx, parts):
        shape = tf.shape(data)
        size = tf.concat(0, [ shape[:1] // parts, shape[1:] ])
        stride = tf.concat(0, [ shape[:1] // parts, shape[1:]*0 ])
        start = stride * idx
        return tf.slice(data, start, size)
    outputs_all = []
    for i in range(len(model.outputs)):
        outputs_all.append([])

#Place a copy of the model on each GPU, each getting a slice of the batch

    for i in range(gpu_count):
        with tf.device('/gpu:%d' % i):
            with tf.name_scope('tower_%d' % i) as scope:
            inputs = []

#Slice each input into a piece for processing on this GPU

            for x in model.inputs:
                input_shape = tuple(x.get_shape().as_list())[1:]
                slice_n = Lambda(get_slice, output_shape=input_shape, arguments={'idx':i,'parts':gpu_count})(x)
                inputs.append(slice_n)
            outputs = model(inputs)

            if not isinstance(outputs, list):
                outputs = [outputs]

#Save all the outputs for merging back together later

            for l in range(len(outputs)):
                outputs_all[l].append(outputs[l])

# merge outputs on CPU

with tf.device('/cpu:0'):
    merged = []
    for outputs in outputs_all:
        merged.append(merge(outputs, mode='concat', concat_axis=0))
    return Model(input=model.inputs, output=merged)

batch_size = 32
nb_classes = 10
nb_epoch = 1000
rows, cols = 32, 32
channels = 3

(X_train, y_train), (X_test, y_test) = cifar10.load_data()
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
print (X_train.shape[1:])

Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

model = Sequential()

model.add(Convolution2D(96, 3, 3, border_mode = 'same', input_shape=(3, 32, 32)))
model.add(Activation('relu'))
model.add(Convolution2D(96, 3, 3,border_mode='same'))
model.add(Activation('relu'))

#The next layer is the substitute of max pooling, we are taking a strided convolution layer to reduce the dimensionality of the image.

model.add(Convolution2D(96, 3, 3, border_mode='same', subsample = (2,2)))
model.add(Dropout(0.5))
model.add(Convolution2D(192, 3, 3, border_mode = 'same'))
model.add(Activation('relu'))
model.add(Convolution2D(192, 3, 3,border_mode='same'))
model.add(Activation('relu'))

# The next layer is the substitute of max pooling, we are taking a strided convolution layer to reduce the dimensionality of the image.

model.add(Convolution2D(192, 3, 3,border_mode='same', subsample = (2,2)))
model.add(Dropout(0.5))
model.add(Convolution2D(192, 3, 3, border_mode = 'same'))
model.add(Activation('relu'))
model.add(Convolution2D(192, 1, 1,border_mode='valid'))
model.add(Activation('relu'))
model.add(Convolution2D(10, 1, 1, border_mode='valid'))

model.add(GlobalAveragePooling2D())
model.add(Activation('softmax'))
model = make_parallel(model, 4)
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])

print (model.summary())

datagen = ImageDataGenerator(
featurewise_center=False,  # set input mean to 0 over the dataset

samplewise_center=False,  # set each sample mean to 0

featurewise_std_normalization=False,  # divide inputs by std of the dataset

samplewise_std_normalization=False,  # divide each input by its std

zca_whitening=False,  # apply ZCA whitening

rotation_range=0,  # randomly rotate images in the range (degrees, 0 to 180)

width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)

height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)

horizontal_flip=False,  # randomly flip images

vertical_flip=False)  # randomly flip images

datagen.fit(X_train)

filepath="weights.{epoch:02d}-{val_loss:.2f}.hdf5"

checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='max')

callbacks_list = [checkpoint]

# Fit the model on the batches generated by datagen.flow().

history_callback = model.fit_generator(datagen.flow(X_train, Y_train, batch_size=batch_size), samples_per_epoch=X_train.shape[0], nb_epoch=nb_epoch, validation_data=(X_test, Y_test), callbacks=callbacks_list, verbose=0)

pandas.DataFrame(history_callback.history).to_csv("history.csv")
model.save('keras_allconv.h5')