keras-issue.py

from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.optimizers import Adamax

import numpy as np
from keras.preprocessing.image import ImageDataGenerator


def main():
    model = Sequential()
    model.add(Convolution2D(32, 3, 3, border_mode='valid', input_shape=(1, 300, 400)))
    model.add(Activation('relu'))
    model.add(Convolution2D(32, 3, 3))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Convolution2D(64, 3, 3, border_mode='valid'))
    model.add(Activation('relu'))
    model.add(Convolution2D(64, 3, 3))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Convolution2D(64, 3, 3, border_mode='valid'))
    model.add(Activation('relu'))
    model.add(Convolution2D(64, 3, 3))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Convolution2D(128, 3, 3, border_mode='valid'))
    model.add(Activation('relu'))
    model.add(Convolution2D(128, 3, 3))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Convolution2D(128, 3, 3, border_mode='valid'))
    model.add(Activation('relu'))
    model.add(Convolution2D(128, 3, 3))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Flatten())

    model.add(Dense(128))
    model.add(Activation('relu'))

    model.add(Dense(128))
    model.add(Activation('relu'))

    model.add(Dense(4))
    model.add(Activation('linear'))

    model.summary()

    adam = Adamax()
    model.compile(loss='mean_squared_error', optimizer=adam)

    X_train = np.zeros((1067, 1, 300, 400), dtype=np.float32)
    Y_train = np.zeros((1067, 4), dtype=np.float32)

    ret_valid = {}
    ret_valid['X'] = np.zeros((356, 1, 300, 400), dtype=np.float32)
    ret_valid['y'] = np.zeros((356, 4), dtype=np.float32)

    datagen = ImageDataGenerator(featurewise_center=False, featurewise_std_normalization=False)
    datagen.fit(X_train)

    model.fit_generator(
        datagen.flow(X_train, Y_train, batch_size=8),
        samples_per_epoch=len(X_train),
        nb_epoch=200,
        validation_data=(ret_valid['X'], ret_valid['y']))

    # model.fit(
    #     X_train, Y_train, batch_size=8,
    #     nb_epoch=200,
    #     validation_data=(ret_valid['X'], ret_valid['y']))

if __name__ == '__main__':
    main()