mnist_cnn_test_freeze

gistfile1.txt

from __future__ import print_function
import numpy as np
np.random.seed(1337)  # for reproducibility

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.utils import np_utils

batch_size = 128
nb_classes = 10
nb_epoch = 12

# input image dimensions
img_rows, img_cols = 28, 28
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
nb_pool = 2
# convolution kernel size
nb_conv = 3

# the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')

import keras
class PerEpoch(keras.callbacks.Callback):
    '''Learning rate monitor, monitor the learning rate and change it conditionally

    # Arguments
        epoch_num: monitor range
        shrinkage: shrinkage of learning rate
    '''
    def __init__(self, model):
        self.epoch = []
        self.history = {}
        self.model = model

    def on_train_begin(self, logs={}):
        self.epoch = []
        self.history = {}
        self.pause_cnt = 0

    def on_epoch_end(self, epoch, logs={}):
        for layer in self.model.layers:
            layer.trainable = False
        print(self.model.get_weights()[2][1][1])
        self.model.compile(optimizer='sgd', loss='categorical_crossentropy')
        return


# convert class vectors to binary class matrices
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(nb_filters, nb_conv, nb_conv,
                        border_mode='valid',
                        input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, nb_conv, nb_conv))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, nb_conv, nb_conv))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))

model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))


#sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer='sgd', loss='categorical_crossentropy')



#for layer in model.layers:
#    layer.trainable = False

per_epoch = PerEpoch(model)

model.fit(X_train[:1000], Y_train[:1000], batch_size=batch_size, nb_epoch=nb_epoch,
          show_accuracy=True, verbose=1, validation_data=(X_test, Y_test),
          callbacks=[per_epoch])
score = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])