Python keras.layers.UpSampling2D() Examples

def build_cae_model(height=32, width=32, channel=3):
    """
    build convolutional autoencoder model
    """
    input_img = Input(shape=(height, width, channel))

    # encoder
    net = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
    net = MaxPooling2D((2, 2), padding='same')(net)
    net = Conv2D(8, (3, 3), activation='relu', padding='same')(net)
    net = MaxPooling2D((2, 2), padding='same')(net)
    net = Conv2D(4, (3, 3), activation='relu', padding='same')(net)
    encoded = MaxPooling2D((2, 2), padding='same', name='enc')(net)

    # decoder
    net = Conv2D(4, (3, 3), activation='relu', padding='same')(encoded)
    net = UpSampling2D((2, 2))(net)
    net = Conv2D(8, (3, 3), activation='relu', padding='same')(net)
    net = UpSampling2D((2, 2))(net)
    net = Conv2D(16, (3, 3), activation='relu', padding='same')(net)
    net = UpSampling2D((2, 2))(net)
    decoded = Conv2D(channel, (3, 3), activation='sigmoid', padding='same')(net)

    return Model(input_img, decoded) 

def build_model():
    model = Sequential()
    model.add(InputLayer(input_shape=(None, None, 1)))
    model.add(Conv2D(8, (3, 3), activation='relu', padding='same', strides=2))
    model.add(Conv2D(8, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(16, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(16, (3, 3), activation='relu', padding='same', strides=2))
    model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(32, (3, 3), activation='relu', padding='same', strides=2))
    model.add(UpSampling2D((2, 2)))
    model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
    model.add(UpSampling2D((2, 2)))
    model.add(Conv2D(16, (3, 3), activation='relu', padding='same'))
    model.add(UpSampling2D((2, 2)))
    model.add(Conv2D(2, (3, 3), activation='tanh', padding='same'))
    # model.compile(optimizer='rmsprop', loss='mse')
    model.compile(optimizer='adam', loss='mse')
    return model


#训练数据 

def g_block(inp, fil, u = True):

    if u:
        out = UpSampling2D(interpolation = 'bilinear')(inp)
    else:
        out = Activation('linear')(inp)

    skip = Conv2D(fil, 1, padding = 'same', kernel_initializer = 'he_normal')(out)

    out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(out)
    out = LeakyReLU(0.2)(out)

    out = Conv2D(filters = fil, kernel_size = 3, padding = 'same', kernel_initializer = 'he_normal')(out)
    out = LeakyReLU(0.2)(out)

    out = Conv2D(fil, 1, padding = 'same', kernel_initializer = 'he_normal')(out)

    out = add([out, skip])
    out = LeakyReLU(0.2)(out)

    return out 

def get_unet_model(input_channel_num=3, out_ch=3, start_ch=64, depth=4, inc_rate=2., activation='relu',
         dropout=0.5, batchnorm=False, maxpool=True, upconv=True, residual=False):
    def _conv_block(m, dim, acti, bn, res, do=0):
        n = Conv2D(dim, 3, activation=acti, padding='same')(m)
        n = BatchNormalization()(n) if bn else n
        n = Dropout(do)(n) if do else n
        n = Conv2D(dim, 3, activation=acti, padding='same')(n)
        n = BatchNormalization()(n) if bn else n

        return Concatenate()([m, n]) if res else n

    def _level_block(m, dim, depth, inc, acti, do, bn, mp, up, res):
        if depth > 0:
            n = _conv_block(m, dim, acti, bn, res)
            m = MaxPooling2D()(n) if mp else Conv2D(dim, 3, strides=2, padding='same')(n)
            m = _level_block(m, int(inc * dim), depth - 1, inc, acti, do, bn, mp, up, res)
            if up:
                m = UpSampling2D()(m)
                m = Conv2D(dim, 2, activation=acti, padding='same')(m)
            else:
                m = Conv2DTranspose(dim, 3, strides=2, activation=acti, padding='same')(m)
            n = Concatenate()([n, m])
            m = _conv_block(n, dim, acti, bn, res)
        else:
            m = _conv_block(m, dim, acti, bn, res, do)

        return m

    i = Input(shape=(None, None, input_channel_num))
    o = _level_block(i, start_ch, depth, inc_rate, activation, dropout, batchnorm, maxpool, upconv, residual)
    o = Conv2D(out_ch, 1)(o)
    model = Model(inputs=i, outputs=o)

    return model 

def yolo_main(input, num_anchors, num_classes):

    darknet_network = Model(input, darknet(input))

    network, network_1 = last_layers(darknet_network.output, 512, num_anchors * (num_classes + 5), layer_name="last1")

    network = NetworkConv2D_BN_Leaky( input=network, channels=256, kernel_size=(1,1))
    network = UpSampling2D(2)(network)
    network = Concatenate()([network, darknet_network.layers[152].output])

    network, network_2 = last_layers(network,  256,  num_anchors * (num_classes + 5), layer_name="last2")

    network = NetworkConv2D_BN_Leaky(input=network, channels=128, kernel_size=(1, 1))
    network = UpSampling2D(2)(network)
    network = Concatenate()([network, darknet_network.layers[92].output])

    network, network_3 = last_layers(network, 128, num_anchors * (num_classes + 5), layer_name="last3")

    return Model(input, [network_1, network_2, network_3]) 

def convolutional_autoencoder():

    input_shape=(28,28,1)
    n_channels = input_shape[-1]
    model = Sequential()
    model.add(Conv2D(32, (3,3), activation='relu', padding='same', input_shape=input_shape))
    model.add(MaxPool2D(padding='same'))
    model.add(Conv2D(16, (3,3), activation='relu', padding='same'))
    model.add(MaxPool2D(padding='same'))
    model.add(Conv2D(8, (3,3), activation='relu', padding='same'))
    model.add(UpSampling2D())
    model.add(Conv2D(16, (3,3), activation='relu', padding='same'))
    model.add(UpSampling2D())
    model.add(Conv2D(32, (3,3), activation='relu', padding='same'))
    model.add(Conv2D(n_channels, (3,3), activation='sigmoid', padding='same'))
    return model 

def test_tiny_conv_upsample_random(self):
        np.random.seed(1988)
        input_dim = 10
        input_shape = (input_dim, input_dim, 1)
        num_kernels = 3
        kernel_height = 5
        kernel_width = 5

        # Define a model
        model = Sequential()
        model.add(
            Conv2D(
                input_shape=input_shape,
                filters=num_kernels,
                kernel_size=(kernel_height, kernel_width),
            )
        )
        model.add(UpSampling2D(size=2))

        # Set some random weights
        model.set_weights([np.random.rand(*w.shape) for w in model.get_weights()])

        # Test the keras model
        self._test_model(model) 

def test_upsample_layer_params(self):
        options = dict(size=[(2, 2), (3, 3), (4, 4), (5, 5)])

        np.random.seed(1988)
        input_dim = 10
        input_shape = (input_dim, input_dim, 1)
        X = np.random.rand(1, *input_shape)

        # Define a function that tests a model
        def build_model(x):
            kwargs = dict(zip(options.keys(), x))
            model = Sequential()
            model.add(Conv2D(filters=5, kernel_size=(7, 7), input_shape=input_shape))
            model.add(UpSampling2D(**kwargs))
            return x, model

        # Iterate through all combinations
        product = itertools.product(*options.values())
        args = [build_model(p) for p in product]

        # Test the cases
        print("Testing a total of %s cases. This could take a while" % len(args))
        for param, model in args:
            self._run_test(model, param) 

def get_autoencoder_model(input_shape, labels=10):
    """
    An autoencoder for MNIST to be used in the DAL implementation.
    """

    image = Input(shape=input_shape)
    encoder = Conv2D(32, (3, 3), activation='relu', padding='same')(image)
    encoder = MaxPooling2D((2, 2), padding='same')(encoder)
    encoder = Conv2D(8, (3, 3), activation='relu', padding='same')(encoder)
    encoder = Conv2D(4, (3, 3), activation='relu', padding='same')(encoder)
    encoder = MaxPooling2D((2, 2), padding='same')(encoder)

    decoder = UpSampling2D((2, 2), name='embedding')(encoder)
    decoder = Conv2D(4, (3, 3), activation='relu', padding='same')(decoder)
    decoder = Conv2D(8, (3, 3), activation='relu', padding='same')(decoder)
    decoder = UpSampling2D((2, 2))(decoder)
    decoder = Conv2D(32, (3, 3), activation='relu', padding='same')(decoder)
    decoder = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(decoder)

    autoencoder = Model(image, decoder)
    return autoencoder 

def _up_block(block,mrge, nb_filters):
    up = merge([Convolution2D(2*nb_filters, 2, 2, border_mode='same')(UpSampling2D(size=(2, 2))(block)), mrge], mode='concat', concat_axis=1)
    # conv = Convolution2D(4*nb_filters, 1, 1, activation='relu', border_mode='same')(up)
    conv = Convolution2D(nb_filters, 3, 3, activation='relu', border_mode='same')(up)
    conv = Convolution2D(nb_filters, 3, 3, activation='relu', border_mode='same')(conv)

    # conv = Convolution2D(4*nb_filters, 1, 1, activation='relu', border_mode='same')(conv)
    # conv = Convolution2D(nb_filters, 3, 3, activation='relu', border_mode='same')(conv)
    # conv = Convolution2D(nb_filters, 1, 1, activation='relu', border_mode='same')(conv)
    
    # conv = Convolution2D(4*nb_filters, 1, 1, activation='relu', border_mode='same')(conv)
    # conv = Convolution2D(nb_filters, 3, 3, activation='relu', border_mode='same')(conv)
    # conv = Convolution2D(nb_filters, 1, 1, activation='relu', border_mode='same')(conv)

    return conv


# http://arxiv.org/pdf/1512.03385v1.pdf
# 50 Layer resnet 

def Upsample2D_block(filters, stage, kernel_size=(3,3), upsample_rate=(2,2),
                     use_batchnorm=False, skip=None):

    def layer(input_tensor):

        conv_name, bn_name, relu_name, up_name = handle_block_names(stage)

        x = UpSampling2D(size=upsample_rate, name=up_name)(input_tensor)

        if skip is not None:
            x = Concatenate()([x, skip])

        x = ConvRelu(filters, kernel_size, use_batchnorm=use_batchnorm,
                     conv_name=conv_name + '1', bn_name=bn_name + '1', relu_name=relu_name + '1')(x)

        x = ConvRelu(filters, kernel_size, use_batchnorm=use_batchnorm,
                     conv_name=conv_name + '2', bn_name=bn_name + '2', relu_name=relu_name + '2')(x)

        return x
    return layer 

def Conv2DUpsample(filters,
                   upsample_rate,
                   kernel_size=(3,3),
                   up_name='up',
                   conv_name='conv',
                   **kwargs):

    def layer(input_tensor):
        x = UpSampling2D(upsample_rate, name=up_name)(input_tensor)
        x = Conv2D(filters,
                   kernel_size,
                   padding='same',
                   name=conv_name,
                   **kwargs)(x)
        return x
    return layer 

def Upsample2D_block(filters, stage, kernel_size=(3,3), upsample_rate=(2,2),
                     use_batchnorm=False, skip=None):

    def layer(input_tensor):

        conv_name, bn_name, relu_name, up_name = handle_block_names(stage)

        x = UpSampling2D(size=upsample_rate, name=up_name)(input_tensor)

        if skip is not None:
            x = Concatenate()([x, skip])

        x = ConvRelu(filters, kernel_size, use_batchnorm=use_batchnorm,
                     conv_name=conv_name + '1', bn_name=bn_name + '1', relu_name=relu_name + '1')(x)

        x = ConvRelu(filters, kernel_size, use_batchnorm=use_batchnorm,
                     conv_name=conv_name + '2', bn_name=bn_name + '2', relu_name=relu_name + '2')(x)

        return x
    return layer 

def Upsample2D_block(filters, stage, kernel_size=(3,3), upsample_rate=(2,2),
                     use_batchnorm=False, skip=None):

    def layer(input_tensor):

        conv_name, bn_name, relu_name, up_name = handle_block_names(stage)

        x = UpSampling2D(size=upsample_rate, name=up_name)(input_tensor)

        if skip is not None:
            x = Concatenate()([x, skip])

        x = ConvRelu(filters, kernel_size, use_batchnorm=use_batchnorm,
                     conv_name=conv_name + '1', bn_name=bn_name + '1', relu_name=relu_name + '1')(x)

        x = ConvRelu(filters, kernel_size, use_batchnorm=use_batchnorm,
                     conv_name=conv_name + '2', bn_name=bn_name + '2', relu_name=relu_name + '2')(x)

        return x
    return layer 

def Conv2DUpsample(filters,
                   upsample_rate,
                   kernel_size=(3,3),
                   up_name='up',
                   conv_name='conv',
                   **kwargs):

    def layer(input_tensor):
        x = UpSampling2D(upsample_rate, name=up_name)(input_tensor)
        x = Conv2D(filters,
                   kernel_size,
                   padding='same',
                   name=conv_name,
                   **kwargs)(x)
        return x
    return layer 

def inception_resnet_v2_fpn(input_shape, channels=1, activation="sigmoid"):
    inceresv2 = InceptionResNetV2Same(input_shape=input_shape, include_top=False)
    conv1, conv2, conv3, conv4, conv5 = inceresv2.output

    P1, P2, P3, P4, P5 = create_pyramid_features(conv1, conv2, conv3, conv4, conv5)
    x = concatenate(
        [
            prediction_fpn_block(P5, "P5", (8, 8)),
            prediction_fpn_block(P4, "P4", (4, 4)),
            prediction_fpn_block(P3, "P3", (2, 2)),
            prediction_fpn_block(P2, "P2"),
        ]
    )
    x = conv_bn_relu(x, 256, 3, (1, 1), name="aggregation")
    x = decoder_block_no_bn(x, 128, conv1, 'up4')
    x = UpSampling2D()(x)
    x = conv_relu(x, 64, 3, (1, 1), name="up5_conv1")
    x = conv_relu(x, 64, 3, (1, 1), name="up5_conv2")
    if activation == 'softmax':
        name = 'mask_softmax'
        x = Conv2D(channels, (1, 1), activation=activation, name=name)(x)
    else:
        x = Conv2D(channels, (1, 1), activation=activation, name="mask")(x)
    model = Model(inceresv2.input, x)
    return model 

def mnist_generator(input_shape=(28, 28, 1), scale=1/4):
    x0 = Input(input_shape)
    x = Conv2D(int(128*scale), (3, 3), strides=(2, 2), padding='same')(x0)
    x = InstanceNormalization()(x)
    x = LeakyReLU()(x)
    x = Conv2D(int(64*scale), (3, 3), strides=(2, 2), padding='same')(x)
    x = InstanceNormalization()(x)
    x = LeakyReLU()(x)
    x = residual_block(x, scale, num_id=2)
    x = residual_block(x, scale*2, num_id=3)
    x = UpSampling2D(size=(2, 2))(x)
    x = Conv2D(int(1024*scale), (1, 1))(x)
    x = InstanceNormalization()(x)
    x = LeakyReLU()(x)
    x = UpSampling2D(size=(2, 2))(x)
    x = Conv2D(1, (1, 1), activation='sigmoid')(x)
    return Model(x0, x) 

def model():
    model = VGG16(include_top=False, input_shape=(128, 128, 3))
    x = model.output

    y = x
    x = Flatten()(x)
    x = Dense(1024, activation='relu')(x)
    x = Dropout(0.5)(x)
    x = Dense(1024, activation='relu')(x)
    x = Dropout(0.5)(x)
    probability = Dense(5, activation='sigmoid', name='probabilistic_output')(x)

    y = UpSampling2D((3, 3))(y)
    y = Activation('relu')(y)
    y = Conv2D(1, (3, 3), activation='linear')(y)
    position = Reshape(target_shape=(10, 10), name='positional_output')(y)
    model = Model(input=model.input, outputs=[probability, position])
    return model 

def apn_module(self, x):

        def right(x):
            x = layers.AveragePooling2D()(x)
            x = layers.Conv2D(self.classes, kernel_size=1, padding='same')(x)
            x = layers.BatchNormalization()(x)
            x = layers.Activation('relu')(x)
            x = layers.UpSampling2D(interpolation='bilinear')(x)
            return x

        def conv(x, filters, kernel_size, stride):
            x = layers.Conv2D(filters, kernel_size=kernel_size, strides=(stride, stride), padding='same')(x)
            x = layers.BatchNormalization()(x)
            x = layers.Activation('relu')(x)
            return x

        x_7 = conv(x, int(x.shape[-1]), 7, stride=2)
        x_5 = conv(x_7, int(x.shape[-1]), 5, stride=2)
        x_3 = conv(x_5, int(x.shape[-1]), 3, stride=2)

        x_3_1 = conv(x_3, self.classes, 3, stride=1)
        x_3_1_up = layers.UpSampling2D(interpolation='bilinear')(x_3_1)
        x_5_1 = conv(x_5, self.classes, 5, stride=1)
        x_3_5 = layers.add([x_5_1, x_3_1_up])
        x_3_5_up = layers.UpSampling2D(interpolation='bilinear')(x_3_5)
        x_7_1 = conv(x_7, self.classes, 3, stride=1)
        x_3_5_7 = layers.add([x_7_1, x_3_5_up])
        x_3_5_7_up = layers.UpSampling2D(interpolation='bilinear')(x_3_5_7)

        x_middle = conv(x, self.classes, 1, stride=1)
        x_middle = layers.multiply([x_3_5_7_up, x_middle])

        x_right = right(x)
        x_middle = layers.add([x_middle, x_right])
        return x_middle 

def decoder(self, x):
        x = self.apn_module(x)
        x = layers.UpSampling2D(size=8, interpolation='bilinear')(x)
        x = layers.Conv2D(self.classes, kernel_size=3, padding='same')(x)
        x = layers.BatchNormalization()(x)
        x = layers.Activation('softmax')(x)
        return x 

def upSampling(x, skip_36, skip_61, layer_idx, num_classes=80):
    out_filters = 3*(num_classes+5)
    yolo_83 = _conv_block(x, [{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': layer_idx},
            {'filter':  out_filters, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': layer_idx+1}], skip=False)

    x = _conv_block(x, [{'filter':  256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': layer_idx+4}],\
                    skip = False)
    x = UpSampling2D(2)(x)
    x = concatenate([x, skip_61])
    x = _conv_block(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': layer_idx+7},
            {'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': layer_idx+8},
            {'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': layer_idx+9},
            {'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': layer_idx+10},
            {'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': layer_idx+11}], skip=False)
  # Layer 92 => 94
    yolo_95 = _conv_block(x, [{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True,  'leaky': True, \
                               'layer_idx': layer_idx+12},
                {'filter': out_filters, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': layer_idx+13}],\
                          skip=False)
  # Layer 95 => 98
    x = _conv_block(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True,   'layer_idx': layer_idx+16}],\
                    skip=False)
    x = UpSampling2D(2)(x)
    x = concatenate([x, skip_36])
  # Layer 99 => 106
    yolo_107 = _conv_block(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True,  'leaky': True, \
                                'layer_idx':layer_idx+19},
                 {'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True,  'leaky': True,  'layer_idx': layer_idx+20},
                 {'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True,  'leaky': True,  'layer_idx': layer_idx+21},
                 {'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True,  'leaky': True,  'layer_idx': layer_idx+22},
                 {'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True,  'leaky': True,  'layer_idx': layer_idx+23},
                 {'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True,  'leaky': True,  'layer_idx': layer_idx+24},
                 {'filter': out_filters, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': layer_idx+25}],\
                           skip=False)
    
    
    return yolo_83, yolo_95, yolo_107

#The midblock is where the spatial pyramid pooling as well as the FC block with change for the YOLOv3-SPP model are reflected 

def decoder(self, encoded):
        decoded = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)
        decoded = UpSampling2D((2, 2))(decoded)
        decoded = Conv2D(8, (3, 3), activation='relu', padding='same')(decoded)
        decoded = UpSampling2D((2, 2))(decoded)
        decoded = Conv2D(16, (3, 3), activation='relu')(decoded)
        decoded = UpSampling2D((2, 2))(decoded)
        decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(decoded)
        return decoded 

def tiny_yolo_main(input, num_anchors, num_classes):
    network_1 = NetworkConv2D_BN_Leaky(input=input, channels=16, kernel_size=(3,3) )
    network_1 = MaxPool2D(pool_size=(2,2), strides=(2,2), padding="same")(network_1)
    network_1 = NetworkConv2D_BN_Leaky(input=network_1, channels=32, kernel_size=(3, 3))
    network_1 = MaxPool2D(pool_size=(2, 2), strides=(2, 2), padding="same")(network_1)
    network_1 = NetworkConv2D_BN_Leaky(input=network_1, channels=64, kernel_size=(3, 3))
    network_1 = MaxPool2D(pool_size=(2, 2), strides=(2, 2), padding="same")(network_1)
    network_1 = NetworkConv2D_BN_Leaky(input=network_1, channels=128, kernel_size=(3, 3))
    network_1 = MaxPool2D(pool_size=(2, 2), strides=(2, 2), padding="same")(network_1)
    network_1 = NetworkConv2D_BN_Leaky(input=network_1, channels=256, kernel_size=(3, 3))

    network_2 = MaxPool2D(pool_size=(2, 2), strides=(2, 2), padding="same")(network_1)
    network_2 = NetworkConv2D_BN_Leaky(input=network_2, channels=512, kernel_size=(3, 3))
    network_2 = MaxPool2D(pool_size=(2, 2), strides=(1, 1), padding="same")(network_2)
    network_2 = NetworkConv2D_BN_Leaky(input=network_2, channels=1024, kernel_size=(3, 3))
    network_2 = NetworkConv2D_BN_Leaky(input=network_2, channels=256, kernel_size=(1, 1))

    network_3 = NetworkConv2D_BN_Leaky(input=network_2, channels=512, kernel_size=(3, 3))
    network_3 = Conv2D(num_anchors * (num_classes + 5),  kernel_size=(1,1))(network_3)

    network_2 = NetworkConv2D_BN_Leaky(input=network_2, channels=128, kernel_size=(1, 1))
    network_2 = UpSampling2D(2)(network_2)

    network_4 = Concatenate()([network_2, network_1])
    network_4 = NetworkConv2D_BN_Leaky(input=network_4, channels=256, kernel_size=(3, 3))
    network_4 = Conv2D(num_anchors * (num_classes + 5), kernel_size=(1,1))(network_4)

    return Model(input, [network_3, network_4]) 

def connect_left_right(left, right, num_channels, num_channels_next, name):
  # left: 2 residual modules
  left = residual(left, num_channels_next, name=name + 'skip.0')
  left = residual(left, num_channels_next, name=name + 'skip.1')

  # up: 2 times residual & nearest neighbour
  out = residual(right, num_channels, name=name + 'out.0')
  out = residual(out, num_channels_next, name=name + 'out.1')
  out = UpSampling2D(name=name + 'out.upsampleNN')(out)
  out = Add(name=name + 'out.add')([left, out])
  return out 

def emit_UpSampling2D(self, IR_node, in_scope=False):
        code = "{:<15} = layers.UpSampling2D(name='{}', size= ({}), data_format = 'channels_last')({})".format(
            IR_node.variable_name,
            IR_node.name,
            IR_node.get_attr('scales'),
            self.parent_variable_name(IR_node))
        return code 

def uk(self, x, k):
        # (up sampling followed by 1x1 convolution <=> fractional-strided 1/2)
        if self.use_resize_convolution:
            x = UpSampling2D(size=(2, 2))(x)  # Nearest neighbor upsampling
            x = ReflectionPadding2D((1, 1))(x)
            x = Conv2D(filters=k, kernel_size=3, strides=1, padding='valid')(x)
        else:
            x = Conv2DTranspose(filters=k, kernel_size=3, strides=2, padding='same')(x)  # this matches fractinoally stided with stride 1/2
        x = self.normalization(axis=3, center=True, epsilon=1e-5)(x, training=True)
        x = Activation('relu')(x)
        return x

#===============================================================================
# Models 

def test_upsample(self):
        """
        Test the conversion of 2D convolutional layer + upsample
        """
        from keras.layers import Convolution2D, UpSampling2D

        # Create a simple Keras model
        model = Sequential()
        model.add(
            Convolution2D(input_shape=(64, 64, 3), nb_filter=32, nb_row=5, nb_col=5)
        )
        model.add(UpSampling2D(size=(2, 2)))
        input_names = ["input"]
        output_names = ["output"]
        spec = keras.convert(model, input_names, output_names).get_spec()
        self.assertIsNotNone(spec)

        # Test the model class
        self.assertIsNotNone(spec.description)
        self.assertTrue(spec.HasField("neuralNetwork"))

        # Test the inputs and outputs
        self.assertEquals(len(spec.description.input), len(input_names))
        six.assertCountEqual(
            self, input_names, [x.name for x in spec.description.input]
        )
        self.assertEquals(len(spec.description.output), len(output_names))
        six.assertCountEqual(
            self, output_names, [x.name for x in spec.description.output]
        )

        # Test the layer parameters.
        layers = spec.neuralNetwork.layers
        layer_0 = layers[0]
        self.assertIsNotNone(layer_0.convolution)
        layer_1 = layers[1]
        self.assertIsNotNone(layer_1.upsample) 

def convolution_image_for_decoding(x, filters, upsample=None, name=None, n_layer=2):
    for i in range(1, n_layer+1):
        x = Convolution2D(filters, (3, 3), activation="elu", padding="same", name="%s/Conv%d" % (name, i))(x)
    if upsample:
        x = UpSampling2D()(x)
    return x 

def create_cnn():
    net = MobileNet(input_shape=(128,128,3), weights=None, include_top=False)
    # upsampling(32->128)
    input = Input((32,32,3))
    x = UpSampling2D(4)(input)
    x = net(x)
    x = GlobalAveragePooling2D()(x)
    x = Dense(10, activation="softmax")(x)

    model = Model(input, x)
    model.summary()
    return model 

def create_cnn():
    net = MobileNet(input_shape=(128,128,3), include_top=False)
    # conv_pw_6から訓練させる(41)
    for i in range(41):
        net.layers[i].trainable = False
    # upsampling(32->128)
    input = Input((32,32,3))
    x = UpSampling2D(4)(input)
    x = net(x)
    x = GlobalAveragePooling2D()(x)
    x = Dense(10, activation="softmax")(x)

    model = Model(input, x)
    model.summary()
    return model