一個縮減版的inception卷積神經網絡用於mnist數據集分類

在這個網絡中僅僅使用了一個inception module。20個epochs後準確率可以達到99.25%。哪位想要測試數據可以聯繫我。主要參考了https://github.com/fchollet/deep-learning-models

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

from keras.models import Model
from keras.models import Sequential
from keras import layers
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D, Input
from keras.layers import BatchNormalization, AveragePooling2D, GlobalAveragePooling2D
from keras.utils import np_utils
from keras import backend as K
from keras.optimizers import Adam
from six.moves import cPickle
import gzip

def conv2d_bn(x,
              filters,
              num_row,
              num_col,
              padding='same',
              strides=(1, 1),
              name=None):
    if name is not None:
        bn_name = name + '_bn'
        conv_name = name + '_conv'
    else:
        bn_name = None
        conv_name = None
    if K.image_data_format() == 'channels_first':
        bn_axis = 1
    else:
        bn_axis = 3
    x = Conv2D(
        filters, (num_row, num_col),
        strides=strides,
        padding=padding,
        use_bias=False,
        name=conv_name)(x)
    x = BatchNormalization(axis=bn_axis, scale=False, name=bn_name)(x)
    x = Activation('relu', name=name)(x)
    return x

batch_size = 50
nb_classes = 10
nb_epoch = 20

# the data, shuffled and split between train and test sets
f = gzip.open('mnist.pkl.gz','rb')
data = cPickle.load(f)
(X_train, y_train), (X_test, y_test), (X_val, y_val) = data

if K.image_dim_ordering() == 'th':
    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_val = X_val.reshape(X_val.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
    X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
    X_val = X_val.reshape(X_val.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

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

# 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)
Y_val = np_utils.to_categorical(y_val, nb_classes)

img_input = Input(shape=(28, 28, 1))

x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)

# mixed 0, 1, 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)

branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)

branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)

branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate(
    [branch1x1, branch5x5, branch3x3dbl, branch_pool],
    axis=3,
    name='mixed0')
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(10, activation='softmax', name='predictions')(x)
model = Model(img_input, x, name='inception_v3')
model.compile(optimizer='adadelta',
              loss='categorical_crossentropy',
              metrics=['accuracy'])
model.fit(X_train, Y_train, batch_size=batch_size, epochs=nb_epoch,
           verbose=1, validation_data=(X_val, Y_val))
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
model.save('toy_inceptionV1.h5')
model.save_weights('toy_inceptionV1_weights.h5')