def ResNet_1(train_ds, classes=10, batch_size=32, epochs=3, depth=20): #32x32
if (depth - 2) % 6 != 0:
raise ValueError('depth should be 6n+2 (eg 20, 32, 44 in [a])')
num_filters = 16
num_res_blocks = int((depth - 2) / 6)
inputs = Input(shape=[32,32,3])
x = resnet_layer(inputs=inputs)
for stack in range(3):
for res_block in range(num_res_blocks):
strides = 1
if stack > 0 and res_block == 0:
strides = 2
y = resnet_layer(inputs=x,num_filters=num_filters,strides=strides)
y = resnet_layer(inputs=y,num_filters=num_filters,activation=None)
x = resnet_layer(inputs=x,num_filters=num_filters,kernel_size=1,strides=strides,activation=None,batch_normalization=False)
x = add([x, y])
x = Activation('relu')(x)
num_filters *= 2
x = AveragePooling2D(pool_size=8)(x)
y = Flatten()(x)
outputs = Dense(classes,
activation='softmax',
kernel_initializer='he_normal')(y)
model = Model(inputs=inputs, outputs=outputs)
model.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=0.001), metrics=['accuracy'])
model.summary()
model.fit(train_ds, batch_size=batch_size, epochs=epochs)
model.save('ResNet_1.model')
def res_chan_attention_blocks(res_in, num_chans, reduction_ratio):
x = resnet_layer(inputs=res_in,
num_filters=num_chans,
kernel_initializer=test_initializer
)
x = attention_layer(x, 4)
return x
def res_blocks(res_in, num_chans):
x = resnet_layer(inputs=res_in,
num_filters=num_chans,
kernel_initializer=test_initializer
)
return x
def res_chan_attention_blocks(res_in, num_chans, reduction_ratio):
x = resnet_layer(inputs=res_in,
num_filters=num_chans
)
x = attention_layer(x, 4)
return x
def res_blocks(res_in, num_chans):
x = resnet_layer(inputs=res_in,
num_filters=num_chans
)
return x
def ResNet_2(train_ds, classes=10, batch_size=32, epochs=3, depth=20): #32x32
if (depth - 2) % 9 != 0:
raise ValueError('depth should be 9n+2 (eg 56 or 110 in [b])')
num_filters_in = 16
num_res_blocks = int((depth - 2) / 9)
inputs = Input(shape=[32,32,3])
x = resnet_layer(inputs=inputs,
num_filters=num_filters_in,
conv_first=True)
for stage in range(3):
for res_block in range(num_res_blocks):
activation = 'relu'
batch_normalization = True
strides = 1
if stage == 0:
num_filters_out = num_filters_in * 4
if res_block == 0:
activation = None
batch_normalization = False
else:
num_filters_out = num_filters_in * 2
if res_block == 0:
strides = 2
y = resnet_layer(inputs=x,
num_filters=num_filters_in,
kernel_size=1,
strides=strides,
activation=activation,
batch_normalization=batch_normalization,
conv_first=False)
y = resnet_layer(inputs=y,
num_filters=num_filters_in,
conv_first=False)
y = resnet_layer(inputs=y,
num_filters=num_filters_out,
kernel_size=1,
conv_first=False)
if res_block == 0:
x = resnet_layer(inputs=x,
num_filters=num_filters_out,
kernel_size=1,
strides=strides,
activation=None,
batch_normalization=False)
x = add([x, y])
num_filters_in = num_filters_out
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=8)(x)
y = Flatten()(x)
outputs = Dense(classes,activation='softmax',kernel_initializer='he_normal')(y)
model = Model(inputs=inputs, outputs=outputs)
model.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=0.001), metrics=['accuracy'])
model.summary()
model.fit(train_ds, batch_size=batch_size, epochs=epochs)
model.save('ResNet_2.model')