def make_gan_model(generator, discriminator, optimizer):
discriminator.trainable = False
gan_model = Sequential()
gan_model.add(generator)
gan_model.add(discriminator)
gan_model.compile(loss='binary_crossentropy',
optimizer=optimizer, metric=None)
return gan_model
def make_discriminator(optimizer):
discriminator = Sequential()
discriminator.add(Dense(2048, input_shape=image_shape))
discriminator.add(LeakyReLU(0.2))
discriminator.add(Dropout(0.3))
discriminator.add(Dense(1024))
discriminator.add(LeakyReLU(0.2))
discriminator.add(Dropout(0.3))
discriminator.add(Dense(512))
discriminator.add(LeakyReLU(0.2))
discriminator.add(Dropout(0.3))
discriminator.add(Dense(256))
discriminator.add(LeakyReLU(0.2))
discriminator.add(Dropout(0.3))
discriminator.add(Dense(1))
discriminator.add(Sigmoid())
discriminator.compile(loss='binary_crossentropy',
optimizer=optimizer,
metric=None)
return discriminator
def make_generator(optimizer):
generator = Sequential()
generator.add(Dense(256, input_shape=randomDim))
generator.add(LeakyReLU(0.2))
generator.add(Dense(512))
generator.add(LeakyReLU(0.2))
generator.add(Dense(1024))
generator.add(LeakyReLU(0.2))
generator.add(Dense(2048))
generator.add(LeakyReLU(0.2))
generator.add(Dense(image_shape))
generator.add(Sigmoid())
return generator
def make_model():
model = Sequential()
model.add(Input(shape=input_shape))
model.add(Dense(4096))
model.add(LeakyReLU(0.2))
model.add(Dense(2048))
model.add(LeakyReLU(0.2))
model.add(Dense(1024))
model.add(LeakyReLU(0.2))
model.add(Dense(512))
model.add(LeakyReLU(0.2))
model.add(Dense(256))
model.add(LeakyReLU(0.2))
model.add(Dense(10))
model.add(Softmax())
model.summary()
model.compile(Momentum(), 'categorical_crossentropy', 'accuracy')
return model
def make_my_yolo(input_shape, num_anchors, num_classes):
ori_c, ori_w, ori_h = input_shape
model = Sequential()
model.add(Input(shape=input_shape))
add_conv2d_bn_leaky(model, 32, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 32, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 64, 3)
add_conv2d_bn_leaky(model, 64, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 64, 3)
add_conv2d_bn_leaky(model, 64, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 128, 3)
add_conv2d_bn_leaky(model, 128, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 128, 3)
add_conv2d_bn_leaky(model, 128, 3)
add_conv2d_bn_leaky(model, 128, 3)
model.add(Conv2D(num_anchors * (4 + 1 + num_classes), 1, 1))
model.add(Reshape((num_anchors, (4 + 1 + num_classes), ori_w // 32, ori_h // 32)))
model.add(Transpose((0, 1, 3, 4, 2)))
mask = np.ones((num_anchors, 7, 7, 7), dtype=bool)
mask[..., 2] = False
mask[..., 3] = False
model.add(MaskedSigmoid(mask))
return model
def make_model():
model = Sequential()
model.add(Input(shape=input_shape))
model.add(Conv2D(32, kernel_size=(3, 3), padding='same'))
model.add(ReLU())
model.add(Dropout(0.3))
model.add(Conv2D(32, kernel_size=(3, 3), padding='same'))
model.add(ReLU())
model.add(MaxPooling2D(2, 2))
model.add(Flatten())
model.add(Dropout(0.3))
model.add(Dense(512, kernel_initializer='He'))
model.add(ReLU())
model.add(Dropout(0.3))
model.add(Dense(10, kernel_initializer='He'))
model.add(Softmax())
model.summary()
model.compile(Adam(), 'categorical_crossentropy', 'accuracy')
return model
def make_model():
model = Sequential()
model.add(Input(shape=input_shape))
model.add(
Conv2D(16,
kernel_size=3,
strides=1,
padding='same',
kernel_regularizer=l2(1e-4)))
model.add(BatchNormalization_v2())
model.add(ReLU())
add_residual_block(model, num_filters=16)
add_residual_block(model, num_filters=16)
add_residual_block(model, num_filters=16)
add_residual_block(model, num_filters=32, strides=2, cnn_shortcut=True)
add_residual_block(model, num_filters=32)
add_residual_block(model, num_filters=32)
add_residual_block(model, num_filters=64, strides=2, cnn_shortcut=True)
add_residual_block(model, num_filters=64)
add_residual_block(model, num_filters=64)
model.add(AveragePooling2DAll())
model.add(Flatten())
model.add(Dense(10, kernel_initializer='He'))
model.add(Softmax())
model.summary()
model.compile(Adam(lr=0.001, decay=1e-4), 'categorical_crossentropy',
'accuracy')
return model
def cnn_seq(num_filters=16,
kernel_size=3,
strides=1,
activation=ReLU,
batch_normalization=True,
conv_first=True):
seq = Sequential()
seq.add(
Conv2D(num_filters,
kernel_size=kernel_size,
strides=strides,
padding='same',
kernel_regularizer=l2(5e-3)))
if batch_normalization:
seq.add(BatchNormalization_v2())
seq.add(activation())
seq.add(
Conv2D(num_filters,
kernel_size=kernel_size,
strides=1,
padding='same',
kernel_regularizer=l2(5e-3)))
if batch_normalization:
seq.add(BatchNormalization_v2())
return seq
def make_darknet19(input_shape):
model = Sequential()
model.add(Input(shape=input_shape))
add_conv2d_bn_leaky(model, 32, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 64, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 128, 3)
add_conv2d_bn_leaky(model, 64, 1)
add_conv2d_bn_leaky(model, 128, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 256, 3)
add_conv2d_bn_leaky(model, 128, 1)
add_conv2d_bn_leaky(model, 256, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 512, 3)
add_conv2d_bn_leaky(model, 256, 1)
add_conv2d_bn_leaky(model, 512, 3)
add_conv2d_bn_leaky(model, 256, 1)
add_conv2d_bn_leaky(model, 512, 3)
model.add(MaxPooling2D(2, 2))
add_conv2d_bn_leaky(model, 1024, 3)
add_conv2d_bn_leaky(model, 512, 1)
add_conv2d_bn_leaky(model, 1024, 3)
add_conv2d_bn_leaky(model, 512, 1)
add_conv2d_bn_leaky(model, 1024, 3)
add_conv2d_bn_leaky(model, 1000, 1)
model.add(Conv2D(5 * (4 + 1 + 1), 1, 1))
return model
def make_model():
model = Sequential()
model.add(Input(shape=input_shape))
model.add(Dense(4096))
model.add(ReLU())
model.add(Dense(4096))
model.add(ReLU())
model.add(Dense(4096))
model.add(ReLU())
model.add(Dense(4096))
model.add(ReLU())
model.add(Dense(4096))
model.add(ReLU())
model.add(Dense(10))
model.add(Softmax())
model.summary()
model.compile(Adam(), 'categorical_crossentropy', 'accuracy')
return model
def resnet_v2(input_shape, depth, num_classes):
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)
model = Sequential()
model.add(Input(shape=input_shape))
add_resnet_layer(model, 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
main_route = Sequential()
add_resnet_layer(main_route, num_filters=num_filters_in, kernel_size=1, strides=strides,
activation=activation, batch_normalization=batch_normalization, conv_first=False)
add_resnet_layer(main_route, num_filters=num_filters_in, conv_first=False)
add_resnet_layer(main_route, num_filters=num_filters_out, kernel_size=1, conv_first=False)
if res_block == 0:
short_cut = Sequential()
add_resnet_layer(short_cut, num_filters=num_filters_out, kernel_size=1,
strides=strides, activation=None, batch_normalization=False)
else:
short_cut = Same()
model.add(Separate())
model.add([short_cut, main_route])
model.add(Add())
num_filters_in = num_filters_out
model.add(BatchNormalization_v2())
model.add(Activation('relu'))
model.add(AveragePooling2DAll())
model.add(Flatten())
model.add(Dense(10, kernel_initializer='He'))
model.add(Softmax())
return model