我们从Python开源项目中，提取了以下12个代码示例，用于说明如何使用keras.layers.convolutional.Conv2DTranspose()。
def make_generator(): """Creates a generator model that takes a 100-dimensional noise vector as a "seed", and outputs images of size 28x28x1.""" model = Sequential() model.add(Dense(1024, input_dim=100)) model.add(LeakyReLU()) model.add(Dense(128 * 7 * 7)) model.add(BatchNormalization()) model.add(LeakyReLU()) if K.image_data_format() == 'channels_first': model.add(Reshape((128, 7, 7), input_shape=(128 * 7 * 7,))) bn_axis = 1 else: model.add(Reshape((7, 7, 128), input_shape=(128 * 7 * 7,))) bn_axis = -1 model.add(Conv2DTranspose(128, (5, 5), strides=2, padding='same')) model.add(BatchNormalization(axis=bn_axis)) model.add(LeakyReLU()) model.add(Convolution2D(64, (5, 5), padding='same')) model.add(BatchNormalization(axis=bn_axis)) model.add(LeakyReLU()) model.add(Conv2DTranspose(64, (5, 5), strides=2, padding='same')) model.add(BatchNormalization(axis=bn_axis)) model.add(LeakyReLU()) # Because we normalized training inputs to lie in the range [-1, 1], # the tanh function should be used for the output of the generator to ensure its output # also lies in this range. model.add(Convolution2D(1, (5, 5), padding='same', activation='tanh')) return model
def __transition_up_block(ip, nb_filters, type='deconv', weight_decay=1E-4): ''' SubpixelConvolutional Upscaling (factor = 2) Args: ip: keras tensor nb_filters: number of layers type: can be 'upsampling', 'subpixel', 'deconv'. Determines type of upsampling performed weight_decay: weight decay factor Returns: keras tensor, after applying upsampling operation. ''' if type == 'upsampling': x = UpSampling2D()(ip) elif type == 'subpixel': x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay), use_bias=False, kernel_initializer='he_normal')(ip) x = SubPixelUpscaling(scale_factor=2)(x) x = Conv2D(nb_filters, (3, 3), activation='relu', padding='same', kernel_regularizer=l2(weight_decay), use_bias=False, kernel_initializer='he_normal')(x) else: x = Conv2DTranspose(nb_filters, (3, 3), activation='relu', padding='same', strides=(2, 2), kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(ip) return x
def GeneratorDeconv(image_size = 64): L = int(image_size) inputs = Input(shape = (100, )) x = Dense(512*int(L/16)**2)(inputs) #shape(512*(L/16)**2,) x = BatchNormalization()(x) x = Activation('relu')(x) x = Reshape((int(L/16), int(L/16), 512))(x) # shape(L/16, L/16, 512) x = Conv2DTranspose(256, (4, 4), strides = (2, 2), kernel_initializer = init, padding = 'same')(x) # shape(L/8, L/8, 256) x = BatchNormalization()(x) x = Activation('relu')(x) x = Conv2DTranspose(128, (4, 4), strides = (2, 2), kernel_initializer = init, padding = 'same')(x) # shape(L/4, L/4, 128) x = BatchNormalization()(x) x = Activation('relu')(x) x = Conv2DTranspose(64, (4, 4), strides = (2, 2), kernel_initializer = init, padding = 'same')(x) # shape(L/2, L/2, 64) x = BatchNormalization()(x) x = Activation('relu')(x) x = Conv2DTranspose(3, (4, 4), strides= (2, 2), kernel_initializer = init, padding = 'same')(x) # shape(L, L, 3) images = Activation('tanh')(x) model = Model(inputs = inputs, outputs = images) model.summary() return model
def bottleneck(encoder, output, upsample=False, reverse_module=False): internal = output // 4 x = Conv2D(internal, (1, 1), use_bias=False)(encoder) x = BatchNormalization(momentum=0.1)(x) x = Activation('relu')(x) if not upsample: x = Conv2D(internal, (3, 3), padding='same', use_bias=True)(x) else: x = Conv2DTranspose(filters=internal, kernel_size=(3, 3), strides=(2, 2), padding='same')(x) x = BatchNormalization(momentum=0.1)(x) x = Activation('relu')(x) x = Conv2D(output, (1, 1), padding='same', use_bias=False)(x) other = encoder if encoder.get_shape()[-1] != output or upsample: other = Conv2D(output, (1, 1), padding='same', use_bias=False)(other) other = BatchNormalization(momentum=0.1)(other) if upsample and reverse_module is not False: other = UpSampling2D(size=(2, 2))(other) if upsample and reverse_module is False: decoder = x else: x = BatchNormalization(momentum=0.1)(x) decoder = add([x, other]) decoder = Activation('relu')(decoder) return decoder
def build(encoder, nc): enet = bottleneck(encoder, 64, upsample=True, reverse_module=True) # bottleneck 4.0 enet = bottleneck(enet, 64) # bottleneck 4.1 enet = bottleneck(enet, 64) # bottleneck 4.2 enet = bottleneck(enet, 16, upsample=True, reverse_module=True) # bottleneck 5.0 enet = bottleneck(enet, 16) # bottleneck 5.1 enet = Conv2DTranspose(filters=nc, kernel_size=(2, 2), strides=(2, 2), padding='same')(enet) return enet
def bottleneck(encoder, output, upsample=False, reverse_module=False): internal = output // 4 x = Conv2D(internal, (1, 1), use_bias=False)(encoder) x = BatchNormalization(momentum=0.1)(x) # x = Activation('relu')(x) x = PReLU(shared_axes=[1, 2])(x) if not upsample: x = Conv2D(internal, (3, 3), padding='same', use_bias=True)(x) else: x = Conv2DTranspose(filters=internal, kernel_size=(3, 3), strides=(2, 2), padding='same')(x) x = BatchNormalization(momentum=0.1)(x) # x = Activation('relu')(x) x = PReLU(shared_axes=[1, 2])(x) x = Conv2D(output, (1, 1), padding='same', use_bias=False)(x) other = encoder if encoder.get_shape()[-1] != output or upsample: other = Conv2D(output, (1, 1), padding='same', use_bias=False)(other) other = BatchNormalization(momentum=0.1)(other) if upsample and reverse_module is not False: other = MaxUnpooling2D()([other, reverse_module]) if upsample and reverse_module is False: decoder = x else: x = BatchNormalization(momentum=0.1)(x) decoder = add([x, other]) # decoder = Activation('relu')(decoder) decoder = PReLU(shared_axes=[1, 2])(decoder) return decoder
def build(encoder, nc): network, index_stack = encoder enet = bottleneck(network, 64, upsample=True, reverse_module=index_stack.pop()) # bottleneck 4.0 enet = bottleneck(enet, 64) # bottleneck 4.1 enet = bottleneck(enet, 64) # bottleneck 4.2 enet = bottleneck(enet, 16, upsample=True, reverse_module=index_stack.pop()) # bottleneck 5.0 enet = bottleneck(enet, 16) # bottleneck 5.1 enet = Conv2DTranspose(filters=nc, kernel_size=(2, 2), strides=(2, 2), padding='same')(enet) return enet
def Deconvolution(f, output_shape, k=2, s=2, **kwargs): """Convenience method for Transposed Convolutions.""" if KERAS_2: return Conv2DTranspose(f, kernel_size=(k, k), output_shape=output_shape, strides=(s, s), data_format=K.image_data_format(), **kwargs) else: return Deconvolution2D(f, k, k, output_shape=output_shape, subsample=(s, s), **kwargs)
def __call__(self): model = Sequential() model.add(Dense(1024, kernel_initializer=self.initializer, \ kernel_regularizer=self.regularizer, input_shape=(self.z_dim,))) model.add(BatchNormalization()) model.add(Activation('relu')) model.add(Dense(7 * 7 * 128, kernel_initializer=self.initializer, \ kernel_regularizer=self.regularizer)) model.add(Reshape((7, 7, 128))) model.add(BatchNormalization()) model.add(Activation('relu')) # Convolution transpose layer model.add(Conv2DTranspose(64, kernel_size=(4, 4), strides=(2, 2), padding='same',\ kernel_initializer=self.initializer, kernel_regularizer=self.regularizer)) model.add(BatchNormalization()) model.add(Activation('relu')) model.add(Conv2DTranspose(1, kernel_size=(4, 4), strides=(2, 2), padding='same',\ kernel_initializer=self.initializer, kernel_regularizer=self.regularizer)) model.add(Activation('sigmoid')) model.add(Reshape((784,))) return model
def bilinear2x(x, nfilters): ''' Ugh, I don't like making layers. My credit goes to: https://kivantium.net/keras-bilinear ''' return Conv2DTranspose(nfilters, (4, 4), strides=(2, 2), padding='same', kernel_initializer=Constant(bilinear_upsample_weights(2, nfilters)))(x)
def build_gen( shape ) : def deconv2d( x, filters, shape=(4, 4) ) : ''' Conv2DTransposed gives me checkerboard artifact... Select one of the 3. ''' # Simpe Conv2DTranspose # Not good, compared to upsample + conv2d below. x= Conv2DTranspose( filters, shape, padding='same', strides=(2, 2), kernel_initializer=Args.kernel_initializer )(x) # simple and works #x = UpSampling2D( (2, 2) )( x ) #x = Conv2D( filters, shape, padding='same' )( x ) # Bilinear2x... Not sure if it is without bug, not tested yet. # Tend to make output blurry though #x = bilinear2x( x, filters ) #x = Conv2D( filters, shape, padding='same' )( x ) x = BatchNormalization(momentum=Args.bn_momentum)( x ) x = LeakyReLU(alpha=Args.alpha_G)( x ) return x # https://github.com/tdrussell/IllustrationGAN z predictor...? # might help. Not sure. noise = Input( shape=Args.noise_shape ) x = noise # 1x1x256 # noise is not useful for generating images. x= Conv2DTranspose( 512, (4, 4), kernel_initializer=Args.kernel_initializer )(x) x = BatchNormalization(momentum=Args.bn_momentum)( x ) x = LeakyReLU(alpha=Args.alpha_G)( x ) # 4x4 x = deconv2d( x, 256 ) # 8x8 x = deconv2d( x, 128 ) # 16x16 x = deconv2d( x, 64 ) # 32x32 # Extra layer x = Conv2D( 64, (3, 3), padding='same', kernel_initializer=Args.kernel_initializer )( x ) x = BatchNormalization(momentum=Args.bn_momentum)( x ) x = LeakyReLU(alpha=Args.alpha_G)( x ) # 32x32 x= Conv2DTranspose( 3, (4, 4), padding='same', activation='tanh', strides=(2, 2), kernel_initializer=Args.kernel_initializer )(x) # 64x64 return models.Model( inputs=noise, outputs=x )
