Python keras.layers.Conv2D() 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 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 d_block(inp, fil, p = True):

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

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

    if p:
        out = AveragePooling2D()(out)

    return out 

def build_model(x_train, num_classes):
        # Reset default graph. Keras leaves old ops in the graph,
        # which are ignored for execution but clutter graph
        # visualization in TensorBoard.
        tf.reset_default_graph()

        inputs = KL.Input(shape=x_train.shape[1:], name="input_image")
        x = KL.Conv2D(32, (3, 3), activation='relu', padding="same",
                      name="conv1")(inputs)
        x = KL.Conv2D(64, (3, 3), activation='relu', padding="same",
                      name="conv2")(x)
        x = KL.MaxPooling2D(pool_size=(2, 2), name="pool1")(x)
        x = KL.Flatten(name="flat1")(x)
        x = KL.Dense(128, activation='relu', name="dense1")(x)
        x = KL.Dense(num_classes, activation='softmax', name="dense2")(x)

        return KM.Model(inputs, x, "digit_classifier_model")

    # Load MNIST Data 

def conv2d(h_num_filters, h_filter_width, h_stride, h_use_bias):

    def compile_fn(di, dh):
        layer = layers.Conv2D(dh['num_filters'], (dh['filter_width'],) * 2,
                              strides=(dh['stride'],) * 2,
                              use_bias=dh['use_bias'],
                              padding='SAME')

        def fn(di):
            return {'out': layer(di['in'])}

        return fn

    return siso_keras_module(
        'Conv2D', compile_fn, {
            'num_filters': h_num_filters,
            'filter_width': h_filter_width,
            'stride': h_stride,
            'use_bias': h_use_bias,
        }) 

def InceptionLayer(self, a, b, c, d):
        def func(x):
            x1 = Conv2D(a, (1, 1), padding='same', activation='relu')(x)
            
            x2 = Conv2D(b, (1, 1), padding='same', activation='relu')(x)
            x2 = Conv2D(b, (3, 3), padding='same', activation='relu')(x2)
            
            x3 = Conv2D(c, (1, 1), padding='same', activation='relu')(x)
            x3 = Conv2D(c, (3, 3), dilation_rate = 2, strides = 1, padding='same', activation='relu')(x3)
            
            x4 = Conv2D(d, (1, 1), padding='same', activation='relu')(x)
            x4 = Conv2D(d, (3, 3), dilation_rate = 3, strides = 1, padding='same', activation='relu')(x4)

            y = Concatenate(axis = -1)([x1, x2, x3, x4])
            
            return y
        return func 

def _conv2d_same(x, filters, prefix, stride=1, kernel_size=3, rate=1):
    # 计算padding的数量，hw是否需要收缩
    if stride == 1:
        return Conv2D(filters,
                      (kernel_size, kernel_size),
                      strides=(stride, stride),
                      padding='same', use_bias=False,
                      dilation_rate=(rate, rate),
                      name=prefix)(x)
    else:
        kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1)
        pad_total = kernel_size_effective - 1
        pad_beg = pad_total // 2
        pad_end = pad_total - pad_beg
        x = ZeroPadding2D((pad_beg, pad_end))(x)
        return Conv2D(filters,
                      (kernel_size, kernel_size),
                      strides=(stride, stride),
                      padding='valid', use_bias=False,
                      dilation_rate=(rate, rate),
                      name=prefix)(x) 

def DCGAN_discriminator():
    nb_filters = 64
    nb_conv = int(np.floor(np.log(128) / np.log(2)))
    list_filters = [nb_filters * min(8, (2 ** i)) for i in range(nb_conv)]

    input_img = Input(shape=(128, 128, 3))
    x = Conv2D(list_filters[0], (3, 3), strides=(2, 2), name="disc_conv2d_1", padding="same")(input_img)
    x = BatchNormalization(axis=-1)(x)
    x = LeakyReLU(0.2)(x)
    # Next convs
    for i, f in enumerate(list_filters[1:]):
        name = "disc_conv2d_%s" % (i + 2)
        x = Conv2D(f, (3, 3), strides=(2, 2), name=name, padding="same")(x)
        x = BatchNormalization(axis=-1)(x)
        x = LeakyReLU(0.2)(x)

    x_flat = Flatten()(x)
    x_out = Dense(1, activation="sigmoid", name="disc_dense")(x_flat)
    discriminator_model = Model(inputs=input_img, outputs=[x_out])
    return discriminator_model 

def _initial_conv_block_inception(input, initial_conv_filters, weight_decay=5e-4):
    ''' Adds an initial conv block, with batch norm and relu for the DPN
    Args:
        input: input tensor
        initial_conv_filters: number of filters for initial conv block
        weight_decay: weight decay factor
    Returns: a keras tensor
    '''
    channel_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = Conv2D(initial_conv_filters, (7, 7), padding='same', use_bias=False, kernel_initializer='he_normal',
               kernel_regularizer=l2(weight_decay), strides=(2, 2))(input)
    x = BatchNormalization(axis=channel_axis)(x)
    x = Activation('relu')(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)

    return x 

def _bn_relu_conv_block(input, filters, kernel=(3, 3), stride=(1, 1), weight_decay=5e-4):
    ''' Adds a Batchnorm-Relu-Conv block for DPN
    Args:
        input: input tensor
        filters: number of output filters
        kernel: convolution kernel size
        stride: stride of convolution
    Returns: a keras tensor
    '''
    channel_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = Conv2D(filters, kernel, padding='same', use_bias=False, kernel_initializer='he_normal',
               kernel_regularizer=l2(weight_decay), strides=stride)(input)
    x = BatchNormalization(axis=channel_axis)(x)
    x = Activation('relu')(x)
    return x 

def _conv_block(inp, convs, skip=True):
  x = inp
  count = 0
  len_convs = len(convs)
  for conv in convs:
    if count == (len_convs - 2) and skip:
      skip_connection = x
    count += 1
    if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # peculiar padding as darknet prefer left and top
    x = Conv2D(conv['filter'],
           conv['kernel'],
           strides=conv['stride'],
           padding='valid' if conv['stride'] > 1 else 'same', # peculiar padding as darknet prefer left and top
           name='conv_' + str(conv['layer_idx']),
           use_bias=False if conv['bnorm'] else True)(x)
    if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
    if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)
  return add([skip_connection, x]) if skip else x


#SPP block uses three pooling layers of sizes [5, 9, 13] with strides one and all outputs together with the input are concatenated to be fed
  #to the FC block 

def conv_2d(filters, kernel_shape, strides, padding, input_shape=None):
    """
    Defines the right convolutional layer according to the
    version of Keras that is installed.
    :param filters: (required integer) the dimensionality of the output
                    space (i.e. the number output of filters in the
                    convolution)
    :param kernel_shape: (required tuple or list of 2 integers) specifies
                         the strides of the convolution along the width and
                         height.
    :param padding: (required string) can be either 'valid' (no padding around
                    input or feature map) or 'same' (pad to ensure that the
                    output feature map size is identical to the layer input)
    :param input_shape: (optional) give input shape if this is the first
                        layer of the model
    :return: the Keras layer
    """
    if LooseVersion(keras.__version__) >= LooseVersion('2.0.0'):
        if input_shape is not None:
            return Conv2D(filters=filters, kernel_size=kernel_shape,
                          strides=strides, padding=padding,
                          input_shape=input_shape)
        else:
            return Conv2D(filters=filters, kernel_size=kernel_shape,
                          strides=strides, padding=padding)
    else:
        if input_shape is not None:
            return Convolution2D(filters, kernel_shape[0], kernel_shape[1],
                                 subsample=strides, border_mode=padding,
                                 input_shape=input_shape)
        else:
            return Convolution2D(filters, kernel_shape[0], kernel_shape[1],
                                 subsample=strides, border_mode=padding) 

def ss_bt(self, x, dilation, strides=(1, 1), padding='same'):
        x1, x2 = self.channel_split(x)
        filters = (int(x.shape[-1]) // self.groups)
        x1 = layers.Conv2D(filters, kernel_size=(3, 1), strides=strides, padding=padding)(x1)
        x1 = layers.Activation('relu')(x1)
        x1 = layers.Conv2D(filters, kernel_size=(1, 3), strides=strides, padding=padding)(x1)
        x1 = layers.BatchNormalization()(x1)
        x1 = layers.Activation('relu')(x1)
        x1 = layers.Conv2D(filters, kernel_size=(3, 1), strides=strides, padding=padding, dilation_rate=(dilation, 1))(
            x1)
        x1 = layers.Activation('relu')(x1)
        x1 = layers.Conv2D(filters, kernel_size=(1, 3), strides=strides, padding=padding, dilation_rate=(1, dilation))(
            x1)
        x1 = layers.BatchNormalization()(x1)
        x1 = layers.Activation('relu')(x1)

        x2 = layers.Conv2D(filters, kernel_size=(1, 3), strides=strides, padding=padding)(x2)
        x2 = layers.Activation('relu')(x2)
        x2 = layers.Conv2D(filters, kernel_size=(3, 1), strides=strides, padding=padding)(x2)
        x2 = layers.BatchNormalization()(x2)
        x2 = layers.Activation('relu')(x2)
        x2 = layers.Conv2D(filters, kernel_size=(1, 3), strides=strides, padding=padding, dilation_rate=(1, dilation))(
            x2)
        x2 = layers.Activation('relu')(x2)
        x2 = layers.Conv2D(filters, kernel_size=(3, 1), strides=strides, padding=padding, dilation_rate=(dilation, 1))(
            x2)
        x2 = layers.BatchNormalization()(x2)
        x2 = layers.Activation('relu')(x2)
        x_concat = layers.concatenate([x1, x2], axis=-1)
        x_add = layers.add([x, x_concat])
        output = self.channel_shuffle(x_add)
        return output 

def down_sample(self, x, filters):
        x_filters = int(x.shape[-1])
        x_conv = layers.Conv2D(filters - x_filters, kernel_size=3, strides=(2, 2), padding='same')(x)
        x_pool = layers.MaxPool2D()(x)
        x = layers.concatenate([x_conv, x_pool], axis=-1)
        x = layers.BatchNormalization()(x)
        x = layers.Activation('relu')(x)
        return x 

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 conv2d_bn(x,
              filters,
              kernel_size,
              strides=1,
              padding='same',
              activation='relu',
              use_bias=False,
              name=None):
    """Utility function to apply conv + BN.

    # Arguments
        x: input tensor.
        filters: filters in `Conv2D`.
        kernel_size: kernel size as in `Conv2D`.
        padding: padding mode in `Conv2D`.
        activation: activation in `Conv2D`.
        strides: strides in `Conv2D`.
        name: name of the ops; will become `name + '_ac'` for the activation
            and `name + '_bn'` for the batch norm layer.

    # Returns
        Output tensor after applying `Conv2D` and `BatchNormalization`.
    """
    x = Conv2D(filters,
               kernel_size,
               strides=strides,
               padding=padding,
               use_bias=use_bias,
               name=name)(x)
    if not use_bias:
        bn_axis = 1 if K.image_data_format() == 'channels_first' else 3
        bn_name = None if name is None else name + '_bn'
        x = BatchNormalization(axis=bn_axis, scale=False, name=bn_name)(x)
    if activation is not None:
        ac_name = None if name is None else name + '_ac'
        x = Activation(activation, name=ac_name)(x)
    return x 

def identity_block(input_tensor, kernel_size, filters, stage, block):
    """The identity block is the block that has no conv layer at shortcut.

    # Arguments
        input_tensor: input tensor
        kernel_size: default 3, the kernel size of middle conv layer at main path
        filters: list of integers, the filters of 3 conv layer at main path
        stage: integer, current stage label, used for generating layer names
        block: 'a','b'keras.., current block label, used for generating layer names

    # Returns
        Output tensor for the block.
    """
    filters1, filters2, filters3 = filters
    if K.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters2, kernel_size,
               padding='same', name=conv_name_base + '2b')(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = layers.add([x, input_tensor])
    x = Activation('relu')(x)
    return x 

def build(self, input_shape):
        assert len(input_shape) == 4
        self.conv1 = Conv2D(filters=self.filters * self.dim_capsule, 
                            kernel_size=self.kernel_size, 
                            strides=self.strides, 
                            padding=self.padding, 
                            name='primarycap_conv2d') 

def CapsuleNet(input_shape, n_class, num_routing):
    """
    The whole capsule network for MNIST recognition.
    """
    # (None, H, W, C)
    x = Input(input_shape)

    conv1 = Conv2D(filters=256, kernel_size=9, padding='valid', activation='relu', name='init_conv')(x)

    # (None, num_capsules, capsule_dim)
    prim_caps = PrimaryCapsules(filters=32, kernel_size=9, dim_capsule=8, padding='valid', strides=(2, 2))(conv1)
    # (None, n_class, dim_vector)
    digit_caps = DigiCaps(num_capsule=n_class, dim_capsule=16, 
            num_routing=num_routing, name='digitcaps')(prim_caps)

    # (None, n_class)
    pred = Length(name='out_caps')(digit_caps)

    # (None, n_class)
    y = Input(shape=(n_class, ))

    # (None, n_class * dim_vector)
    masked = Mask()([digit_caps, y])  

    x_recon = layers.Dense(512, activation='relu')(masked)
    x_recon = layers.Dense(1024, activation='relu')(x_recon)
    x_recon = layers.Dense(784, activation='sigmoid')(x_recon)
    x_recon = layers.Reshape(target_shape=[28, 28, 1], name='out_recon')(x_recon)

    # two-input-two-output keras Model
    return Model([x, y], [pred, x_recon]) 

def generator(self):

        if self.G:
            return self.G

        #Inputs
        inp = Input(shape = [latent_size])

        #Latent

        #Actual Model
        x = Dense(4*4*16*cha, kernel_initializer = 'he_normal')(inp)
        x = Reshape([4, 4, 16*cha])(x)

        x = g_block(x, 16 * cha, u = False)  #4
        x = g_block(x, 8 * cha)  #8
        x = g_block(x, 4 * cha)  #16
        x = g_block(x, 3 * cha)   #32
        x = g_block(x, 2 * cha)   #64
        x = g_block(x, 1 * cha)   #128

        x = Conv2D(filters = 3, kernel_size = 1, activation = 'sigmoid', padding = 'same', kernel_initializer = 'he_normal')(x)

        self.G = Model(inputs = inp, outputs = x)

        return self.G 

def identity_block(input_tensor, kernel_size, filters, stage, block,
                   use_bias=True, train_bn=True):
    """The identity_block is the block that has no conv layer at shortcut
    # Arguments
        input_tensor: input tensor
        kernel_size: default 3, the kernel size of middle conv layer at main path
        filters: list of integers, the nb_filters of 3 conv layer at main path
        stage: integer, current stage label, used for generating layer names
        block: 'a','b'..., current block label, used for generating layer names
        use_bias: Boolean. To use or not use a bias in conv layers.
        train_bn: Boolean. Train or freeze Batch Norm layers
    """
    nb_filter1, nb_filter2, nb_filter3 = filters
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = KL.Conv2D(nb_filter1, (1, 1), name=conv_name_base + '2a',
                  use_bias=use_bias)(input_tensor)
    x = BatchNorm(name=bn_name_base + '2a')(x, training=train_bn)
    x = KL.Activation('relu')(x)

    x = KL.Conv2D(nb_filter2, (kernel_size, kernel_size), padding='same',
                  name=conv_name_base + '2b', use_bias=use_bias)(x)
    x = BatchNorm(name=bn_name_base + '2b')(x, training=train_bn)
    x = KL.Activation('relu')(x)

    x = KL.Conv2D(nb_filter3, (1, 1), name=conv_name_base + '2c',
                  use_bias=use_bias)(x)
    x = BatchNorm(name=bn_name_base + '2c')(x, training=train_bn)

    x = KL.Add()([x, input_tensor])
    x = KL.Activation('relu', name='res' + str(stage) + block + '_out')(x)
    return x 

def conv_block(input_tensor, kernel_size, filters, stage, block,
               strides=(2, 2), use_bias=True, train_bn=True):
    """conv_block is the block that has a conv layer at shortcut
    # Arguments
        input_tensor: input tensor
        kernel_size: default 3, the kernel size of middle conv layer at main path
        filters: list of integers, the nb_filters of 3 conv layer at main path
        stage: integer, current stage label, used for generating layer names
        block: 'a','b'..., current block label, used for generating layer names
        use_bias: Boolean. To use or not use a bias in conv layers.
        train_bn: Boolean. Train or freeze Batch Norm layers
    Note that from stage 3, the first conv layer at main path is with subsample=(2,2)
    And the shortcut should have subsample=(2,2) as well
    """
    nb_filter1, nb_filter2, nb_filter3 = filters
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = KL.Conv2D(nb_filter1, (1, 1), strides=strides,
                  name=conv_name_base + '2a', use_bias=use_bias)(input_tensor)
    x = BatchNorm(name=bn_name_base + '2a')(x, training=train_bn)
    x = KL.Activation('relu')(x)

    x = KL.Conv2D(nb_filter2, (kernel_size, kernel_size), padding='same',
                  name=conv_name_base + '2b', use_bias=use_bias)(x)
    x = BatchNorm(name=bn_name_base + '2b')(x, training=train_bn)
    x = KL.Activation('relu')(x)

    x = KL.Conv2D(nb_filter3, (1, 1), name=conv_name_base +
                  '2c', use_bias=use_bias)(x)
    x = BatchNorm(name=bn_name_base + '2c')(x, training=train_bn)

    shortcut = KL.Conv2D(nb_filter3, (1, 1), strides=strides,
                         name=conv_name_base + '1', use_bias=use_bias)(input_tensor)
    shortcut = BatchNorm(name=bn_name_base + '1')(shortcut, training=train_bn)

    x = KL.Add()([x, shortcut])
    x = KL.Activation('relu', name='res' + str(stage) + block + '_out')(x)
    return x 

def resnet_graph(input_image, architecture, stage5=False, train_bn=True):
    """Build a ResNet graph.
        architecture: Can be resnet50 or resnet101
        stage5: Boolean. If False, stage5 of the network is not created
        train_bn: Boolean. Train or freeze Batch Norm layers
    """
    assert architecture in ["resnet50", "resnet101"]
    # Stage 1
    x = KL.ZeroPadding2D((3, 3))(input_image)
    x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
    x = BatchNorm(name='bn_conv1')(x, training=train_bn)
    x = KL.Activation('relu')(x)
    C1 = x = KL.MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
    # Stage 2
    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), train_bn=train_bn)
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', train_bn=train_bn)
    C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', train_bn=train_bn)
    # Stage 3
    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', train_bn=train_bn)
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', train_bn=train_bn)
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', train_bn=train_bn)
    C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', train_bn=train_bn)
    # Stage 4
    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', train_bn=train_bn)
    block_count = {"resnet50": 5, "resnet101": 22}[architecture]
    for i in range(block_count):
        x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i), train_bn=train_bn)
    C4 = x
    # Stage 5
    if stage5:
        x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', train_bn=train_bn)
        x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', train_bn=train_bn)
        C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', train_bn=train_bn)
    else:
        C5 = None
    return [C1, C2, C3, C4, C5]


############################################################
#  Proposal Layer
############################################################ 

def rpn_graph(feature_map, anchors_per_location, anchor_stride):
    """Builds the computation graph of Region Proposal Network.
    feature_map: backbone features [batch, height, width, depth]
    anchors_per_location: number of anchors per pixel in the feature map
    anchor_stride: Controls the density of anchors. Typically 1 (anchors for
                   every pixel in the feature map), or 2 (every other pixel).
    Returns:
        rpn_class_logits: [batch, H * W * anchors_per_location, 2] Anchor classifier logits (before softmax)
        rpn_probs: [batch, H * W * anchors_per_location, 2] Anchor classifier probabilities.
        rpn_bbox: [batch, H * W * anchors_per_location, (dy, dx, log(dh), log(dw))] Deltas to be
                  applied to anchors.
    """
    # TODO: check if stride of 2 causes alignment issues if the feature map
    # is not even.
    # Shared convolutional base of the RPN
    shared = KL.Conv2D(512, (3, 3), padding='same', activation='relu',
                       strides=anchor_stride,
                       name='rpn_conv_shared')(feature_map)

    # Anchor Score. [batch, height, width, anchors per location * 2].
    x = KL.Conv2D(2 * anchors_per_location, (1, 1), padding='valid',
                  activation='linear', name='rpn_class_raw')(shared)

    # Reshape to [batch, anchors, 2]
    rpn_class_logits = KL.Lambda(
        lambda t: tf.reshape(t, [tf.shape(t)[0], -1, 2]))(x)

    # Softmax on last dimension of BG/FG.
    rpn_probs = KL.Activation(
        "softmax", name="rpn_class_xxx")(rpn_class_logits)

    # Bounding box refinement. [batch, H, W, anchors per location * depth]
    # where depth is [x, y, log(w), log(h)]
    x = KL.Conv2D(anchors_per_location * 4, (1, 1), padding="valid",
                  activation='linear', name='rpn_bbox_pred')(shared)

    # Reshape to [batch, anchors, 4]
    rpn_bbox = KL.Lambda(lambda t: tf.reshape(t, [tf.shape(t)[0], -1, 4]))(x)

    return [rpn_class_logits, rpn_probs, rpn_bbox] 

def conv2d_with_relu(filters, kernel_size):
    return hke.siso_keras_module_from_keras_layer_fn(lambda: Conv2D(
        filters, kernel_size, padding='same', activation='relu', use_bias=False
    ), {},
                                                     name="Conv2D") 

def conv2d(h_filters, h_kernel_size, stride):
    return hke.siso_keras_module_from_keras_layer_fn(
        lambda filters, kernel_size: Conv2D(
            filters, kernel_size, padding='same', strides=stride), {
                "filters": h_filters,
                "kernel_size": h_kernel_size
            }) 

def conv2d_with_relu(filters, kernel_size):
    return hke.siso_keras_module_from_keras_layer_fn(
        lambda: Conv2D(filters, kernel_size, padding='same', activation='relu', use_bias=False),
        {}, name="Conv2D") 

def init_model(self, dl_rate):
        x = Input(shape = (IMGWIDTH, IMGWIDTH, 3))
        
        x1 = Conv2D(16, (3, 3), dilation_rate = dl_rate, strides = 1, padding='same', activation = 'relu')(x)
        x1 = Conv2D(4, (1, 1), padding='same', activation = 'relu')(x1)
        x1 = BatchNormalization()(x1)
        x1 = MaxPooling2D(pool_size=(8, 8), padding='same')(x1)

        y = Flatten()(x1)
        y = Dropout(0.5)(y)
        y = Dense(1, activation = 'sigmoid')(y)
        return KerasModel(inputs = x, outputs = y) 

def init_model(self): 
        x = Input(shape = (IMGWIDTH, IMGWIDTH, 3))
        
        x1 = Conv2D(8, (3, 3), padding='same', activation = 'relu')(x)
        x1 = BatchNormalization()(x1)
        x1 = MaxPooling2D(pool_size=(2, 2), padding='same')(x1)
        
        x2 = Conv2D(8, (5, 5), padding='same', activation = 'relu')(x1)
        x2 = BatchNormalization()(x2)
        x2 = MaxPooling2D(pool_size=(2, 2), padding='same')(x2)
        
        x3 = Conv2D(16, (5, 5), padding='same', activation = 'relu')(x2)
        x3 = BatchNormalization()(x3)
        x3 = MaxPooling2D(pool_size=(2, 2), padding='same')(x3)
        
        x4 = Conv2D(16, (5, 5), padding='same', activation = 'relu')(x3)
        x4 = BatchNormalization()(x4)
        x4 = MaxPooling2D(pool_size=(4, 4), padding='same')(x4)
        
        y = Flatten()(x4)
        y = Dropout(0.5)(y)
        y = Dense(16)(y)
        y = LeakyReLU(alpha=0.1)(y)
        y = Dropout(0.5)(y)
        y = Dense(1, activation = 'sigmoid')(y)

        return KerasModel(inputs = x, outputs = y)