def get_vgg_full_graph(self, weights_path=None, with_output=True):
model = Graph()
model.add_input(name='input', input_shape=(3, 224, 224))
model.add_node(ZeroPadding2D((1, 1)), name='pad1', input='input')
model.add_node(Convolution2D(64, 3, 3, activation='relu'), name='conv1', input='pad1')
model.add_node(ZeroPadding2D((1, 1)), name='pad2', input='conv1')
model.add_node(Convolution2D(64, 3, 3, activation='relu'), name='conv2', input='pad2')
model.add_node(MaxPooling2D((2, 2), strides=(2, 2)), name='pool1', input='conv2')
model.add_node(ZeroPadding2D((1, 1)), name='pad3', input='pool1')
model.add_node(Convolution2D(128, 3, 3, activation='relu'), name='conv3', input='pad3')
model.add_node(ZeroPadding2D((1, 1)), name='pad4', input='conv3')
model.add_node(Convolution2D(128, 3, 3, activation='relu'), name='conv4', input='pad4')
model.add_node(MaxPooling2D((2, 2), strides=(2, 2)), name='pool2', input='conv4')
model.add_node(ZeroPadding2D((1, 1)), name='pad5', input='pool2')
model.add_node(Convolution2D(256, 3, 3, activation='relu'), name='conv5', input='pad5')
model.add_node(ZeroPadding2D((1, 1)), name='pad6', input='conv5')
model.add_node(Convolution2D(256, 3, 3, activation='relu'), name='conv6', input='pad6')
model.add_node(ZeroPadding2D((1, 1)), name='pad7', input='conv6')
model.add_node(Convolution2D(256, 3, 3, activation='relu'), name='conv7', input='pad7')
model.add_node(MaxPooling2D((2, 2), strides=(2, 2)), name='pool3', input='conv7')
model.add_node(ZeroPadding2D((1, 1)), name='pad8', input='pool3')
model.add_node(Convolution2D(512, 3, 3, activation='relu'), name='conv8', input='pad8')
model.add_node(ZeroPadding2D((1, 1)), name='pad9', input='conv8')
model.add_node(Convolution2D(512, 3, 3, activation='relu'), name='conv9', input='pad9')
model.add_node(ZeroPadding2D((1, 1)), name='pad10', input='conv9')
model.add_node(Convolution2D(512, 3, 3, activation='relu'), name='conv10', input='pad10')
model.add_node(MaxPooling2D((2, 2), strides=(2, 2)), name='pool4', input='conv10')
model.add_node(ZeroPadding2D((1, 1)), name='pad11', input='pool4')
model.add_node(Convolution2D(512, 3, 3, activation='relu'), name='conv11', input='pad11')
model.add_node(ZeroPadding2D((1, 1)), name='pad12', input='conv11')
model.add_node(Convolution2D(512, 3, 3, activation='relu'), name='conv12', input='pad12')
model.add_node(ZeroPadding2D((1, 1)), name='pad13', input='conv12')
model.add_node(Convolution2D(512, 3, 3, activation='relu'), name='conv13', input='pad13')
model.add_node(MaxPooling2D((2, 2), strides=(2, 2)), name='pool5', input='conv13')
model.add_node(Flatten(), name='flat', input='pool5')
model.add_node(Dense(4096, activation='relu'), name='dense1', input='flat')
model.add_node(Dropout(0.5), name='drop1', input='dense1')
model.add_node(Dense(4096, activation='relu'), name='dense2', input='drop1')
model.add_node(Dropout(0.5), name='drop2', input='dense2')
model.add_node(Dense(1000, activation='softmax'), name='dense3', input='drop2')
if with_output:
model.add_output(input='dense3', name='output')
if weights_path:
model.load_weights(weights_path)
return model
python类ZeroPadding2D()的实例源码
def VGG_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def VGG_16(weights_path = None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
#Remove the last two layers to get the 4096D activations
model = pop(model)
model = pop(model)
return model
def VGG_16(weights_path = None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def __init__(self, **kwargs):
super(KerasVGG16, self).__init__(**kwargs)
norm_shape = self.norm_shape
model = Sequential()
model.add(ZeroPadding2D((1,1), input_shape=(norm_shape[0], norm_shape[1], 1),
))
model.add(Convolution2D(64, (3, 3), activation='relu', ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(64, (3, 3), activation='relu', ))
model.add(MaxPooling2D((2,2), strides=(2,2), ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(128, (3, 3), activation='relu', ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(128, (3, 3), activation='relu', ))
model.add(MaxPooling2D((2,2), strides=(2,2), ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(256, (3, 3), activation='relu', ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(256, (3, 3), activation='relu', ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(256, (3, 3), activation='relu', ))
model.add(MaxPooling2D((2,2), strides=(2,2), ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(512, (3, 3), activation='relu', ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(512, (3, 3), activation='relu', ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(512, (3, 3), activation='relu', ))
model.add(MaxPooling2D((2,2), strides=(2,2), ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(512, (3, 3), activation='relu', ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(512, (3, 3), activation='relu', ))
model.add(ZeroPadding2D((1,1), ))
model.add(Convolution2D(512, (3, 3), activation='relu', ))
model.add(MaxPooling2D((2,2), strides=(2,2), ))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(self.max_n_label, activation='softmax'))
# initiate RMSprop optimizer
opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)
# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
self.model = model
def VGG_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def get_deep_anime_model(n_outputs=1000, input_size=128):
'''The deep neural network used for deep anime bot'''
conv = Sequential()
conv.add(Convolution2D(64, 3, 3, activation='relu', input_shape=(3, input_size, input_size)))
conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(64, 3, 3, activation='relu'))
conv.add(MaxPooling2D((2, 2), strides=(2, 2)))
conv.add(BatchNormalization())
# conv.add(Dropout(0.5))
conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(128, 3, 3, activation='relu'))
# conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(128, 1, 1, activation='relu'))
conv.add(MaxPooling2D((2, 2), strides=(2, 2)))
conv.add(BatchNormalization())
# conv.add(Dropout(0.5))
conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(256, 3, 3, activation='relu'))
conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(256, 3, 3, activation='relu'))
# conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(256, 1, 1, activation='relu'))
conv.add(MaxPooling2D((2, 2), strides=(2, 2)))
conv.add(BatchNormalization())
# conv.add(Dropout(0.5))
conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(512, 3, 3, activation='relu'))
conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(512, 3, 3, activation='relu'))
# conv.add(ZeroPadding2D((1, 1)))
conv.add(Convolution2D(512, 1, 1, activation='relu'))
conv.add(AveragePooling2D((8, 8), strides=(2, 2)))
conv.add(BatchNormalization())
# conv.add(Dropout(0.5))
# conv.add(ZeroPadding2D((1, 1)))
# conv.add(Convolution2D(512, 3, 3, activation='relu'))
# conv.add(ZeroPadding2D((1, 1)))
# conv.add(Convolution2D(512, 3, 3, activation='relu'))
# #conv.add(ZeroPadding2D((1, 1)))
# conv.add(Convolution2D(512, 1, 1, activation='relu'))
# conv.add(AveragePooling2D((4, 4)))
# conv.add(BatchNormalization())
conv.add(Flatten())
conv.add(Dropout(0.5))
conv.add(Dense(2048))
conv.add(BatchNormalization())
conv.add(Dropout(0.7))
conv.add(Dense(2048))
conv.add(BatchNormalization())
conv.add(Dropout(0.7))
conv.add(Dense(n_outputs))
conv.add(Activation('softmax'))
print(conv.summary())
return conv
def VGG_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def model_structure_file(self):
return os.path.join(self.current_directory(),
'deep_drive_model_structure.json')
# def _create_feature_layers(self, target_size):
# feature_layer_1 = [
# Convolution2D(96, 11, 11, subsample=(4, 4), dim_ordering='th', activation='relu', input_shape=(3, target_size[0], target_size[1]), name='conv1'),
# MaxPooling2D(pool_size=(3, 3), strides=(2, 2), dim_ordering='th', name='pool1'),
# LRN2D(alpha=0.0001, k=1, beta=0.75, n=5, name='norm1')
# ]
#
# feature_layer_2 = [
# ZeroPadding2D(padding=(2, 2), name='conv2_zeropadding'),
# Convolution2D(256, 5, 5, subsample=(1, 1), dim_ordering='th', activation='relu', name='conv2'),
# MaxPooling2D(pool_size=(3, 3), strides=(2, 2), dim_ordering='th', name='pool2'),
# LRN2D(alpha=0.0001, k=1, beta=0.75, n=5, name='norm2')
# ]
#
# feature_layer_3 = [
# ZeroPadding2D(padding=(1, 1), name='conv3_zeropadding'),
# Convolution2D(384, 3, 3, subsample=(1, 1), dim_ordering='th', activation='relu', name='conv3')
# ]
#
# feature_layer_4 = [
# ZeroPadding2D(padding=(1, 1), name='conv4_zeropadding'),
# Convolution2D(384, 3, 3, subsample=(1, 1), dim_ordering='th', activation='relu', name='conv4')
# ]
#
# feature_layer_5 = [
# ZeroPadding2D(padding=(1, 1), name='conv5_zeropadding'),
# Convolution2D(256, 3, 3, subsample=(1, 1), dim_ordering='th', activation='relu', name='conv5'),
# MaxPooling2D(pool_size=(3, 3), strides=(2, 2), dim_ordering='th', name='pool5')
# ]
#
# return feature_layer_1 + \
# feature_layer_2 + \
# feature_layer_3 + \
# feature_layer_4 + \
# feature_layer_5
#
# def _create_classification_layers(self):
# classification_layers = [
# Flatten(),
# Dense(4096, activation='relu', name='fc6_gtanet'),
# Dropout(0.5),
# Dense(4096, activation='relu', name='fc7_gtanet'),
# Dropout(0.5),
# Dense(6, activation='relu', name='gtanet_fctop')
# ]
# return classification_layers
def vgg_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1, 1), input_shape=(3, 224, 224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def VGG_16(weights_path=None): #??keras??????VGG_16??
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def VGG_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
#top layer of the VGG net
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def VGG_16_Terrassa(weights_path=""):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu',trainable = False))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu',trainable = False))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu',trainable = False))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu',trainable = False))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu',trainable = False))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu',trainable = False))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu',trainable = False))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu',trainable = False))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu',trainable = False))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu',trainable = False))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu',trainable = False))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu',trainable = False))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu',trainable = False))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu',trainable = False))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu',trainable = False))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
print ("Weights Loaded")
model.load_weights(weights_path)
model.layers.pop()
model.layers.pop()
model.outputs = [model.layers[-1].output]
model.layers[-1].outbound_nodes = []
model.add(Dense(13, activation='softmax'))
return model
def VGG_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def VGG_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
#Remove the last two layers to get the 4096D activations
model = pop(model)
model = pop(model)
return model
def VGG_16(X_train, y_train, X_test, y_test, batch_size = 20, nb_classes = 10, nb_epoch = 100):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=X_train[0].shape))
model.add(Convolution2D(64, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
model.add(ZeroPadding2D((1,1)))
#model.add(Convolution2D(512, 3, 3, border_mode='valid', activation='relu', init='glorot_normal'))
#model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
#sgd = SGD(lr=0.005, decay = 1e-6, momentum = 0.9, nesterov=True)
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
# initializes early stopping callback
early_stopping = EarlyStopping(monitor='val_loss', patience=2, verbose=1, mode='auto')
model.compile(loss = 'categorical_crossentropy', optimizer = sgd)
model.fit(X_train, y_train, show_accuracy=True, verbose=1,
callbacks = [early_stopping], batch_size= batch_size, nb_epoch=nb_epoch,
validation_data=(X_test, y_test))
return model, model.evaluate(X_test, y_test, show_accuracy=True, verbose=1)
spatial_stream_cnn.py 文件源码
项目：Video-Classification-2-Stream-CNN
作者: wadhwasahil
项目源码
文件源码
阅读 16
收藏 0
点赞 0
评论 0
def VGG_16(img_rows,img_cols,weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,img_rows,img_cols)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.9))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.8))
model.add(Dense(20, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def VGG_16_test(weights_path='saved_models/best_model_VGG_16/weights_16.h5', shape = 112):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,shape,shape)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
# testing purposes only!
def VGG_19_test(weights_path='saved_models/best_model_VGG_19/weights_19.h5', shape = 112):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,shape,shape)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def VGG_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1, 1), input_shape=(224, 224, 3)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
