def yolo_body(inputs, num_anchors, num_classes):
    """Create YOLO_V2 model CNN body in Keras."""
    darknet = Model(inputs, darknet_body()(inputs))
    conv20 = compose(
        DarknetConv2D_BN_Leaky(1024, (3, 3)),
        DarknetConv2D_BN_Leaky(1024, (3, 3)))(darknet.output)

    conv13 = darknet.layers[43].output
    conv21 = DarknetConv2D_BN_Leaky(64, (1, 1))(conv13)
    # TODO: Allow Keras Lambda to use func arguments for output_shape?
    conv21_reshaped = Lambda(
        space_to_depth_x2,
        output_shape=space_to_depth_x2_output_shape,
        name='space_to_depth')(conv21)

    x = concatenate([conv21_reshaped, conv20])
    x = DarknetConv2D_BN_Leaky(1024, (3, 3))(x)
    x = DarknetConv2D(num_anchors * (num_classes + 5), (1, 1))(x)
    return Model(inputs, x) 

def loss_net(x_in, trux_x_in,width, height,style_image_path,content_weight,style_weight):
    # Append the initial input to the FastNet input to the VGG inputs
    x = concatenate([x_in, trux_x_in], axis=0)
    
    # Normalize the inputs via custom VGG Normalization layer
    x = VGGNormalize(name="vgg_normalize")(x)

    vgg = VGG16(include_top=False,input_tensor=x)

    vgg_output_dict = dict([(layer.name, layer.output) for layer in vgg.layers[-18:]])
    vgg_layers = dict([(layer.name, layer) for layer in vgg.layers[-18:]])

    if style_weight > 0:
        add_style_loss(vgg,style_image_path , vgg_layers, vgg_output_dict, width, height,style_weight)   

    if content_weight > 0:
        add_content_loss(vgg_layers,vgg_output_dict,content_weight)

    # Freeze all VGG layers
    for layer in vgg.layers[-19:]:
        layer.trainable = False

    return vgg 

def block_inception_a(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 96, 1, 1)

    branch_1 = conv2d_bn(input, 64, 1, 1)
    branch_1 = conv2d_bn(branch_1, 96, 3, 3)

    branch_2 = conv2d_bn(input, 64, 1, 1)
    branch_2 = conv2d_bn(branch_2, 96, 3, 3)
    branch_2 = conv2d_bn(branch_2, 96, 3, 3)

    branch_3 = AveragePooling2D((3,3), strides=(1,1), padding='same')(input)
    branch_3 = conv2d_bn(branch_3, 96, 1, 1)

    x = concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis)
    return x 

def block_reduction_a(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 384, 3, 3, strides=(2,2), padding='valid')

    branch_1 = conv2d_bn(input, 192, 1, 1)
    branch_1 = conv2d_bn(branch_1, 224, 3, 3)
    branch_1 = conv2d_bn(branch_1, 256, 3, 3, strides=(2,2), padding='valid')

    branch_2 = MaxPooling2D((3,3), strides=(2,2), padding='valid')(input)

    x = concatenate([branch_0, branch_1, branch_2], axis=channel_axis)
    return x 

def block_inception_b(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 384, 1, 1)

    branch_1 = conv2d_bn(input, 192, 1, 1)
    branch_1 = conv2d_bn(branch_1, 224, 1, 7)
    branch_1 = conv2d_bn(branch_1, 256, 7, 1)

    branch_2 = conv2d_bn(input, 192, 1, 1)
    branch_2 = conv2d_bn(branch_2, 192, 7, 1)
    branch_2 = conv2d_bn(branch_2, 224, 1, 7)
    branch_2 = conv2d_bn(branch_2, 224, 7, 1)
    branch_2 = conv2d_bn(branch_2, 256, 1, 7)

    branch_3 = AveragePooling2D((3,3), strides=(1,1), padding='same')(input)
    branch_3 = conv2d_bn(branch_3, 128, 1, 1)

    x = concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis)
    return x 

def block_reduction_b(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 192, 1, 1)
    branch_0 = conv2d_bn(branch_0, 192, 3, 3, strides=(2, 2), padding='valid')

    branch_1 = conv2d_bn(input, 256, 1, 1)
    branch_1 = conv2d_bn(branch_1, 256, 1, 7)
    branch_1 = conv2d_bn(branch_1, 320, 7, 1)
    branch_1 = conv2d_bn(branch_1, 320, 3, 3, strides=(2,2), padding='valid')

    branch_2 = MaxPooling2D((3, 3), strides=(2, 2), padding='valid')(input)

    x = concatenate([branch_0, branch_1, branch_2], axis=channel_axis)
    return x 

def concat_images_with_tiled_vector(images, vector):
    """Combine a set of images with a vector, tiling the vector at each pixel in the images and concatenating on the channel axis.

    # Params

        images: list of images with the same dimensions
        vector: vector to tile on each image. If you have
            more than one vector, simply concatenate them
            all before calling this function.

    # Returns

    """
    with K.name_scope('concat_images_with_tiled_vector'):
        if not isinstance(images, list):
            images = [images]
        image_shape = K.int_shape(images[0])
        tiled_vector = tile_vector_as_image_channels(vector, image_shape)
        images.append(tiled_vector)
        combined = K.concatenate(images)

        return combined 

def block_inception_a(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 96, 1, 1)

    branch_1 = conv2d_bn(input, 64, 1, 1)
    branch_1 = conv2d_bn(branch_1, 96, 3, 3)

    branch_2 = conv2d_bn(input, 64, 1, 1)
    branch_2 = conv2d_bn(branch_2, 96, 3, 3)
    branch_2 = conv2d_bn(branch_2, 96, 3, 3)

    branch_3 = AveragePooling2D((3,3), strides=(1,1), padding='same')(input)
    branch_3 = conv2d_bn(branch_3, 96, 1, 1)

    x = concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis)
    return x 

def block_reduction_a(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 384, 3, 3, strides=(2,2), padding='valid')

    branch_1 = conv2d_bn(input, 192, 1, 1)
    branch_1 = conv2d_bn(branch_1, 224, 3, 3)
    branch_1 = conv2d_bn(branch_1, 256, 3, 3, strides=(2,2), padding='valid')

    branch_2 = MaxPooling2D((3,3), strides=(2,2), padding='valid')(input)

    x = concatenate([branch_0, branch_1, branch_2], axis=channel_axis)
    return x 

def block_inception_b(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 384, 1, 1)

    branch_1 = conv2d_bn(input, 192, 1, 1)
    branch_1 = conv2d_bn(branch_1, 224, 1, 7)
    branch_1 = conv2d_bn(branch_1, 256, 7, 1)

    branch_2 = conv2d_bn(input, 192, 1, 1)
    branch_2 = conv2d_bn(branch_2, 192, 7, 1)
    branch_2 = conv2d_bn(branch_2, 224, 1, 7)
    branch_2 = conv2d_bn(branch_2, 224, 7, 1)
    branch_2 = conv2d_bn(branch_2, 256, 1, 7)

    branch_3 = AveragePooling2D((3,3), strides=(1,1), padding='same')(input)
    branch_3 = conv2d_bn(branch_3, 128, 1, 1)

    x = concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis)
    return x 

def block_reduction_b(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 192, 1, 1)
    branch_0 = conv2d_bn(branch_0, 192, 3, 3, strides=(2, 2), padding='valid')

    branch_1 = conv2d_bn(input, 256, 1, 1)
    branch_1 = conv2d_bn(branch_1, 256, 1, 7)
    branch_1 = conv2d_bn(branch_1, 320, 7, 1)
    branch_1 = conv2d_bn(branch_1, 320, 3, 3, strides=(2,2), padding='valid')

    branch_2 = MaxPooling2D((3, 3), strides=(2, 2), padding='valid')(input)

    x = concatenate([branch_0, branch_1, branch_2], axis=channel_axis)
    return x 

def forward(self):
        model_input = Input(shape=(self.maxlen,), dtype='int32', name='token')
        x = Token_Embedding(model_input, self.nb_tokens, self.embedding_dim,
                            self.token_embeddings, True, self.maxlen,
                            self.embed_dropout_rate, name='token_embeddings')
        x = Activation('tanh')(x)

        # skip-connection from embedding to output eases gradient-flow and allows access to lower-level features
        # ordering of the way the merge is done is important for consistency with the pretrained model
        lstm_0_output = Bidirectional(
            LSTM(self.rnn_size, return_sequences=True), name="bi_lstm_0")(x)
        lstm_1_output = Bidirectional(
            LSTM(self.rnn_size, return_sequences=True), name="bi_lstm_1")(lstm_0_output)
        x = concatenate([lstm_1_output, lstm_0_output, x], name='concatenate')

        x = self.attention_layer(x)
        if self.return_attention:
            x, weights = x
        outputs = tc_output_logits(x, self.nb_classes, self.final_dropout_rate)
        if self.return_attention:
            outputs.append(weights)
            outputs = concatenate(outputs, axis=-1, name='outputs')

        self.model = Model(inputs=model_input,
                           outputs=outputs, name="Bi_LSTM_Attention") 

def forward(self):
        model_input = Input(shape=(self.maxlen,), dtype='int32', name='token')
        x = Token_Embedding(model_input, self.nb_tokens, self.embedding_dim,
                            self.token_embeddings, False, self.maxlen,
                            self.embed_dropout_rate, name='token_embeddings')
        cnn_combine = []
        for i in range(len(self.conv_kernel_size)):
            cnn = self.cnn_list[i](x)
            pool = self.pool_list[i](cnn)
            cnn_combine.append(pool)
        x = concatenate(cnn_combine, axis=-1)

        x = Flatten()(x)
        x = Dropout(self.final_dropout_rate)(x)
        x = self.fc(x)

        outputs = tc_output_logits(x, self.nb_classes, self.final_dropout_rate)

        self.model = Model(inputs=model_input,
                           outputs=outputs, name="TextCNN") 

def block_inception_a(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 96, 1, 1)

    branch_1 = conv2d_bn(input, 64, 1, 1)
    branch_1 = conv2d_bn(branch_1, 96, 3, 3)

    branch_2 = conv2d_bn(input, 64, 1, 1)
    branch_2 = conv2d_bn(branch_2, 96, 3, 3)
    branch_2 = conv2d_bn(branch_2, 96, 3, 3)

    branch_3 = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(input)
    branch_3 = conv2d_bn(branch_3, 96, 1, 1)

    x = concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis)
    return x 

def block_reduction_a(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 384, 3, 3, strides=(2, 2), padding='valid')

    branch_1 = conv2d_bn(input, 192, 1, 1)
    branch_1 = conv2d_bn(branch_1, 224, 3, 3)
    branch_1 = conv2d_bn(branch_1, 256, 3, 3, strides=(2, 2), padding='valid')

    branch_2 = MaxPooling2D((3, 3), strides=(2, 2), padding='valid')(input)

    x = concatenate([branch_0, branch_1, branch_2], axis=channel_axis)
    return x 

def block_inception_b(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 384, 1, 1)

    branch_1 = conv2d_bn(input, 192, 1, 1)
    branch_1 = conv2d_bn(branch_1, 224, 1, 7)
    branch_1 = conv2d_bn(branch_1, 256, 7, 1)

    branch_2 = conv2d_bn(input, 192, 1, 1)
    branch_2 = conv2d_bn(branch_2, 192, 7, 1)
    branch_2 = conv2d_bn(branch_2, 224, 1, 7)
    branch_2 = conv2d_bn(branch_2, 224, 7, 1)
    branch_2 = conv2d_bn(branch_2, 256, 1, 7)

    branch_3 = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(input)
    branch_3 = conv2d_bn(branch_3, 128, 1, 1)

    x = concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis)
    return x 

def block_reduction_b(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 192, 1, 1)
    branch_0 = conv2d_bn(branch_0, 192, 3, 3, strides=(2, 2), padding='valid')

    branch_1 = conv2d_bn(input, 256, 1, 1)
    branch_1 = conv2d_bn(branch_1, 256, 1, 7)
    branch_1 = conv2d_bn(branch_1, 320, 7, 1)
    branch_1 = conv2d_bn(branch_1, 320, 3, 3, strides=(2, 2), padding='valid')

    branch_2 = MaxPooling2D((3, 3), strides=(2, 2), padding='valid')(input)

    x = concatenate([branch_0, branch_1, branch_2], axis=channel_axis)
    return x 

def block_inception_c(input):
    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 256, 1, 1)

    branch_1 = conv2d_bn(input, 384, 1, 1)
    branch_10 = conv2d_bn(branch_1, 256, 1, 3)
    branch_11 = conv2d_bn(branch_1, 256, 3, 1)
    branch_1 = concatenate([branch_10, branch_11], axis=channel_axis)

    branch_2 = conv2d_bn(input, 384, 1, 1)
    branch_2 = conv2d_bn(branch_2, 448, 3, 1)
    branch_2 = conv2d_bn(branch_2, 512, 1, 3)
    branch_20 = conv2d_bn(branch_2, 256, 1, 3)
    branch_21 = conv2d_bn(branch_2, 256, 3, 1)
    branch_2 = concatenate([branch_20, branch_21], axis=channel_axis)

    branch_3 = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(input)
    branch_3 = conv2d_bn(branch_3, 256, 1, 1)

    x = concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis)
    return x 

def get_unet_resnet(input_shape):
    resnet_base = ResNet50(input_shape=input_shape, include_top=False)

    if args.show_summary:
        resnet_base.summary()

    for l in resnet_base.layers:
        l.trainable = True
    conv1 = resnet_base.get_layer("activation_1").output
    conv2 = resnet_base.get_layer("activation_10").output
    conv3 = resnet_base.get_layer("activation_22").output
    conv4 = resnet_base.get_layer("activation_40").output
    conv5 = resnet_base.get_layer("activation_49").output

    up6 = concatenate([UpSampling2D()(conv5), conv4], axis=-1)
    conv6 = conv_block_simple(up6, 256, "conv6_1")
    conv6 = conv_block_simple(conv6, 256, "conv6_2")

    up7 = concatenate([UpSampling2D()(conv6), conv3], axis=-1)
    conv7 = conv_block_simple(up7, 192, "conv7_1")
    conv7 = conv_block_simple(conv7, 192, "conv7_2")

    up8 = concatenate([UpSampling2D()(conv7), conv2], axis=-1)
    conv8 = conv_block_simple(up8, 128, "conv8_1")
    conv8 = conv_block_simple(conv8, 128, "conv8_2")

    up9 = concatenate([UpSampling2D()(conv8), conv1], axis=-1)
    conv9 = conv_block_simple(up9, 64, "conv9_1")
    conv9 = conv_block_simple(conv9, 64, "conv9_2")

    vgg = VGG16(input_shape=input_shape, input_tensor=resnet_base.input, include_top=False)
    for l in vgg.layers:
        l.trainable = False
    vgg_first_conv = vgg.get_layer("block1_conv2").output
    up10 = concatenate([UpSampling2D()(conv9), resnet_base.input, vgg_first_conv], axis=-1)
    conv10 = conv_block_simple(up10, 32, "conv10_1")
    conv10 = conv_block_simple(conv10, 32, "conv10_2")
    conv10 = SpatialDropout2D(0.2)(conv10)
    x = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv10)
    model = Model(resnet_base.input, x)
    return model 

def get_simple_unet(input_shape):
    img_input = Input(input_shape)
    conv1 = conv_block_simple(img_input, 32, "conv1_1")
    conv1 = conv_block_simple(conv1, 32, "conv1_2")
    pool1 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool1")(conv1)

    conv2 = conv_block_simple(pool1, 64, "conv2_1")
    conv2 = conv_block_simple(conv2, 64, "conv2_2")
    pool2 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool2")(conv2)

    conv3 = conv_block_simple(pool2, 128, "conv3_1")
    conv3 = conv_block_simple(conv3, 128, "conv3_2")
    pool3 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool3")(conv3)

    conv4 = conv_block_simple(pool3, 256, "conv4_1")
    conv4 = conv_block_simple(conv4, 256, "conv4_2")
    conv4 = conv_block_simple(conv4, 256, "conv4_3")

    up5 = concatenate([UpSampling2D()(conv4), conv3], axis=-1)
    conv5 = conv_block_simple(up5, 128, "conv5_1")
    conv5 = conv_block_simple(conv5, 128, "conv5_2")

    up6 = concatenate([UpSampling2D()(conv5), conv2], axis=-1)
    conv6 = conv_block_simple(up6, 64, "conv6_1")
    conv6 = conv_block_simple(conv6, 64, "conv6_2")

    up7 = concatenate([UpSampling2D()(conv6), conv1], axis=-1)
    conv7 = conv_block_simple(up7, 32, "conv7_1")
    conv7 = conv_block_simple(conv7, 32, "conv7_2")

    conv7 = SpatialDropout2D(0.2)(conv7)

    prediction = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv7)
    model = Model(img_input, prediction)
    return model 

def get_unet_mobilenet(input_shape):
    base_model = MobileNet(include_top=False, input_shape=input_shape)

    conv1 = base_model.get_layer('conv_pw_1_relu').output
    conv2 = base_model.get_layer('conv_pw_3_relu').output
    conv3 = base_model.get_layer('conv_pw_5_relu').output
    conv4 = base_model.get_layer('conv_pw_11_relu').output
    conv5 = base_model.get_layer('conv_pw_13_relu').output
    up6 = concatenate([UpSampling2D()(conv5), conv4], axis=-1)
    conv6 = conv_block_simple(up6, 256, "conv6_1")
    conv6 = conv_block_simple(conv6, 256, "conv6_2")

    up7 = concatenate([UpSampling2D()(conv6), conv3], axis=-1)
    conv7 = conv_block_simple(up7, 256, "conv7_1")
    conv7 = conv_block_simple(conv7, 256, "conv7_2")

    up8 = concatenate([UpSampling2D()(conv7), conv2], axis=-1)
    conv8 = conv_block_simple(up8, 192, "conv8_1")
    conv8 = conv_block_simple(conv8, 128, "conv8_2")

    up9 = concatenate([UpSampling2D()(conv8), conv1], axis=-1)
    conv9 = conv_block_simple(up9, 96, "conv9_1")
    conv9 = conv_block_simple(conv9, 64, "conv9_2")

    up10 = concatenate([UpSampling2D()(conv9), base_model.input], axis=-1)
    conv10 = conv_block_simple(up10, 48, "conv10_1")
    conv10 = conv_block_simple(conv10, 32, "conv10_2")
    conv10 = SpatialDropout2D(0.2)(conv10)
    x = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv10)
    model = Model(base_model.input, x)
    return model 

def get_unet_inception_resnet_v2(input_shape):
    base_model = InceptionResNetV2(include_top=False, input_shape=input_shape)
    conv1 = base_model.get_layer('activation_3').output
    conv2 = base_model.get_layer('activation_5').output
    conv3 = base_model.get_layer('block35_10_ac').output
    conv4 = base_model.get_layer('block17_20_ac').output
    conv5 = base_model.get_layer('conv_7b_ac').output
    up6 = concatenate([UpSampling2D()(conv5), conv4], axis=-1)
    conv6 = conv_block_simple(up6, 256, "conv6_1")
    conv6 = conv_block_simple(conv6, 256, "conv6_2")

    up7 = concatenate([UpSampling2D()(conv6), conv3], axis=-1)
    conv7 = conv_block_simple(up7, 256, "conv7_1")
    conv7 = conv_block_simple(conv7, 256, "conv7_2")

    up8 = concatenate([UpSampling2D()(conv7), conv2], axis=-1)
    conv8 = conv_block_simple(up8, 128, "conv8_1")
    conv8 = conv_block_simple(conv8, 128, "conv8_2")

    up9 = concatenate([UpSampling2D()(conv8), conv1], axis=-1)
    conv9 = conv_block_simple(up9, 64, "conv9_1")
    conv9 = conv_block_simple(conv9, 64, "conv9_2")

    up10 = concatenate([UpSampling2D()(conv9), base_model.input], axis=-1)
    conv10 = conv_block_simple(up10, 48, "conv10_1")
    conv10 = conv_block_simple(conv10, 32, "conv10_2")
    conv10 = SpatialDropout2D(0.4)(conv10)
    x = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv10)
    model = Model(base_model.input, x)
    return model 

def preprocessing_fnn(x):
        if len(x[0].shape) == 1:
            p = np.concatenate(x)
            p.shape = (1, p.shape[0])
        else:
            p = np.concatenate(x, axis=1)
        return p 

def _SPP_block(inp, kernels, strides):
    pools = [MaxPool2D(pool_size = pool_size, strides = stride, padding = 'same')(inp) \
             for pool_size, stride in zip(kernels, strides)]
    pools = [inp] + pools
    return concatenate(pools)


#Downsampling block is common to all YOLO-v3 models and are unaffected by the SPP or fully connected blocks or the number of labes 

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 yolo_boxes_to_corners(box_xy, box_wh):
    """Convert YOLO box predictions to bounding box corners."""
    box_mins = box_xy - (box_wh / 2.)
    box_maxes = box_xy + (box_wh / 2.)

    return K.concatenate([
        box_mins[..., 1:2],  # y_min
        box_mins[..., 0:1],  # x_min
        box_maxes[..., 1:2],  # y_max
        box_maxes[..., 0:1]  # x_max
    ]) 

def pyramid_pooling_block(input_tensor, bin_sizes):
    concat_list = [input_tensor]
    h = input_tensor.shape[1].value
    w = input_tensor.shape[2].value

    for bin_size in bin_sizes:
        x = AveragePooling2D(pool_size=(h//bin_size, w//bin_size), strides=(h//bin_size, w//bin_size))(input_tensor)
        x = Conv2D(512, kernel_size=1)(x)
        x = Lambda(lambda x: tf.image.resize_images(x, (h, w)))(x)

        concat_list.append(x)

    return concatenate(concat_list) 

def pyramid_pooling_block(input_tensor, bin_sizes):
    concat_list = [input_tensor]
    h = input_tensor.shape[1].value
    w = input_tensor.shape[2].value

    for bin_size in bin_sizes:
        x = AveragePooling2D(pool_size=(h//bin_size, w//bin_size), strides=(h//bin_size, w//bin_size))(input_tensor)
        x = Conv2D(512, kernel_size=1)(x)
        x = Lambda(lambda x: tf.image.resize_images(x, (h, w)))(x)

        concat_list.append(x)

    return concatenate(concat_list) 

def pyramid_pooling_block(input_tensor, bin_sizes):
    concat_list = [input_tensor]
    h = input_tensor.shape[1].value
    w = input_tensor.shape[2].value

    for bin_size in bin_sizes:
        x = AveragePooling2D(pool_size=(h//bin_size, w//bin_size), strides=(h//bin_size, w//bin_size))(input_tensor)
        x = Conv2D(512, kernel_size=1)(x)
        x = Lambda(lambda x: tf.image.resize_images(x, (h, w)))(x)

        concat_list.append(x)

    return concatenate(concat_list) 

def __dense_block(x, nb_layers, nb_filter, growth_rate, bottleneck=False, dropout_rate=None, weight_decay=1e-4,
                  grow_nb_filters=True, return_concat_list=False):
    ''' Build a dense_block where the output of each conv_block is fed to subsequent ones
    Args:
        x: keras tensor
        nb_layers: the number of layers of conv_block to append to the model.
        nb_filter: number of filters
        growth_rate: growth rate
        bottleneck: bottleneck block
        dropout_rate: dropout rate
        weight_decay: weight decay factor
        grow_nb_filters: flag to decide to allow number of filters to grow
        return_concat_list: return the list of feature maps along with the actual output
    Returns: keras tensor with nb_layers of conv_block appended
    '''
    concat_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x_list = [x]

    for i in range(nb_layers):
        cb = __conv_block(x, growth_rate, bottleneck, dropout_rate, weight_decay)
        x_list.append(cb)

        x = concatenate([x, cb], axis=concat_axis)

        if grow_nb_filters:
            nb_filter += growth_rate

    # global context block
    x = global_context_block(x)

    if return_concat_list:
        return x, nb_filter, x_list
    else:
        return x, nb_filter