Python keras.layers.normalization.BatchNormalization() Examples

def ann_model(input_shape):

    inp = Input(shape=input_shape, name='mfcc_in')
    model = inp

    model = Conv1D(filters=12, kernel_size=(3), activation='relu')(model)
    model = Conv1D(filters=12, kernel_size=(3), activation='relu')(model)
    model = Flatten()(model)

    model = Dense(56)(model)
    model = Activation('relu')(model)
    model = BatchNormalization()(model)
    model = Dropout(0.2)(model)
    model = Dense(28)(model)
    model = Activation('relu')(model)
    model = BatchNormalization()(model)

    model = Dense(1)(model)
    model = Activation('sigmoid')(model)

    model = Model(inp, model)
    return model 

def conv_block(input_tensor, filters, strides, d_rates):
    x = Conv2D(filters[0], kernel_size=1, dilation_rate=d_rates[0])(input_tensor)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[1], kernel_size=3, strides=strides, padding='same', dilation_rate=d_rates[1])(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[2], kernel_size=1, dilation_rate=d_rates[2])(x)
    x = BatchNormalization()(x)

    shortcut = Conv2D(filters[2], kernel_size=1, strides=strides)(input_tensor)
    shortcut = BatchNormalization()(shortcut)

    x = add([x, shortcut])
    x = Activation('relu')(x)

    return x 

def identity_block(input_tensor, filters, d_rates):
    x = Conv2D(filters[0], kernel_size=1, dilation_rate=d_rates[0])(input_tensor)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[1], kernel_size=3, padding='same', dilation_rate=d_rates[1])(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[2], kernel_size=1, dilation_rate=d_rates[2])(x)
    x = BatchNormalization()(x)

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

    return x 

def conv_block(input_tensor, filters, strides, d_rates):
    x = Conv2D(filters[0], kernel_size=1, dilation_rate=d_rates[0])(input_tensor)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[1], kernel_size=3, strides=strides, padding='same', dilation_rate=d_rates[1])(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[2], kernel_size=1, dilation_rate=d_rates[2])(x)
    x = BatchNormalization()(x)

    shortcut = Conv2D(filters[2], kernel_size=1, strides=strides)(input_tensor)
    shortcut = BatchNormalization()(shortcut)

    x = add([x, shortcut])
    x = Activation('relu')(x)

    return x 

def conv_block(input_tensor, filters, strides, d_rates):
    x = Conv2D(filters[0], kernel_size=1, dilation_rate=d_rates[0])(input_tensor)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[1], kernel_size=3, strides=strides, padding='same', dilation_rate=d_rates[1])(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[2], kernel_size=1, dilation_rate=d_rates[2])(x)
    x = BatchNormalization()(x)

    shortcut = Conv2D(filters[2], kernel_size=1, strides=strides)(input_tensor)
    shortcut = BatchNormalization()(shortcut)

    x = add([x, shortcut])
    x = Activation('relu')(x)

    return x 

def identity_block(input_tensor, filters, d_rates):
    x = Conv2D(filters[0], kernel_size=1, dilation_rate=d_rates[0])(input_tensor)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[1], kernel_size=3, padding='same', dilation_rate=d_rates[1])(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[2], kernel_size=1, dilation_rate=d_rates[2])(x)
    x = BatchNormalization()(x)

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

    return x 

def get_residual_model(is_mnist=True, img_channels=1, img_rows=28, img_cols=28):
    model = keras.models.Sequential()
    first_layer_channel = 128
    if is_mnist: # size to be changed to 32,32
        model.add(ZeroPadding2D((2,2), input_shape=(img_channels, img_rows, img_cols))) # resize (28,28)-->(32,32)
        # the first conv 
        model.add(Convolution2D(first_layer_channel, 3, 3, border_mode='same'))
    else:
        model.add(Convolution2D(first_layer_channel, 3, 3, border_mode='same', input_shape=(img_channels, img_rows, img_cols)))

    model.add(Activation('relu'))
    # [residual-based Conv layers]
    residual_blocks = design_for_residual_blocks(num_channel_input=first_layer_channel)
    model.add(residual_blocks)
    model.add(BatchNormalization(axis=1))
    model.add(Activation('relu'))
    # [Classifier]    
    model.add(Flatten())
    model.add(Dense(nb_classes))
    model.add(Activation('softmax'))
    # [END]
    return model 

def makecnn(learningrate,regular,decay,channel_number):
    #model structure
    model=Sequential()
    model.add(Conv3D(100, kernel_size=(3,3,3), strides=(1, 1, 1), input_shape = (20,20,20,channel_number),padding='valid', data_format='channels_last', dilation_rate=(1, 1, 1),  use_bias=True, kernel_initializer='glorot_normal', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=l2(regular), kernel_constraint=None, bias_constraint=None))
    model.add(BatchNormalization())
    model.add(LeakyReLU(0.2))
    #model.add(Dropout(0.3))

    model.add(Conv3D(200, kernel_size=(3,3,3), strides=(1, 1, 1), padding='valid', data_format='channels_last', dilation_rate=(1, 1, 1), use_bias=True, kernel_initializer='glorot_normal', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=l2(regular), kernel_constraint=None, bias_constraint=None))
    model.add(BatchNormalization())
    model.add(LeakyReLU(0.2))
    #model.add(Dropout(0.3))

    model.add(MaxPooling3D(pool_size=(2, 2, 2), strides=None, padding='valid', data_format='channels_last'))
    model.add(BatchNormalization(axis=1, momentum=0.99, epsilon=0.001, center=True, scale=True, beta_initializer='zeros', gamma_initializer='ones', moving_mean_initializer='zeros', moving_variance_initializer='ones', beta_regularizer=None, gamma_regularizer=None, beta_constraint=None, gamma_constraint=None))
    model.add(Conv3D(400, kernel_size=(3,3,3),strides=(1, 1, 1), padding='valid', data_format='channels_last', dilation_rate=(1, 1, 1), use_bias=True, kernel_initializer='glorot_normal', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=l2(regular), kernel_constraint=None, bias_constraint=None))
    model.add(BatchNormalization())
    model.add(LeakyReLU(0.2))
    #model.add(Dropout(0.3))

    model.add(MaxPooling3D(pool_size=(2, 2, 2), strides=None, padding='valid', data_format='channels_last'))
    model.add(Flatten())
    model.add(Dropout(0.3))
    model.add(Dense(1000, use_bias=True, input_shape = (32000,),kernel_initializer='glorot_normal', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=l2(regular), kernel_constraint=None, bias_constraint=None))
    model.add(BatchNormalization())
    model.add(LeakyReLU(0.2))
    model.add(Dropout(0.3))

    model.add(Dense(100, use_bias=True, kernel_initializer='glorot_normal', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=l2(regular), kernel_constraint=None, bias_constraint=None))
    model.add(BatchNormalization())
    model.add(LeakyReLU(0.2))
    model.add(Dropout(0.3))

    model.add(Dense(1, activation='sigmoid', use_bias=True, kernel_initializer='glorot_normal', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=l2(regular), kernel_constraint=None, bias_constraint=None))
    nadam=Nadam(lr=learningrate, beta_1=0.9, beta_2=0.999, epsilon=1e-08, schedule_decay=decay)
    model.compile(loss='binary_crossentropy', optimizer=nadam, metrics=['accuracy',f1score,precision,recall])
    return model 

def conv_factory(x, concat_axis, nb_filter,
                 dropout_rate=None, weight_decay=1E-4):
    x = BatchNormalization(axis=concat_axis,
                           gamma_regularizer=l2(weight_decay),
                           beta_regularizer=l2(weight_decay))(x)
    x = Activation('relu')(x)
    x = Conv2D(nb_filter, (5, 5), dilation_rate=(2, 2),
               kernel_initializer="he_uniform",
               padding="same",
               kernel_regularizer=l2(weight_decay))(x)
    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    return x


# define dense block 

def discriminator(img_dim,alpha=0.2):
    model = Sequential()
    model.add(
            Conv2D(64, kernel_size=5,strides=2,
            padding='same',
            input_shape=img_dim)
            )
    model.add(LeakyReLU(alpha))
    model.add(Conv2D(128,kernel_size=5,strides=2,padding='same'))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha))
    model.add(Conv2D(256,kernel_size=5,strides=2,padding='same'))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha))
    model.add(Flatten())
    model.add(Dense(1))
    model.add(Activation('sigmoid'))
    return model

# Define a combination of Generator and Discriminator 

def __transition_block(ip, nb_filter, compression=1.0, weight_decay=1e-4):
    ''' Apply BatchNorm, Relu 1x1, Conv2D, optional compression, dropout and Maxpooling2D
    Args:
        ip: keras tensor
        nb_filter: number of filters
        compression: calculated as 1 - reduction. Reduces the number of feature maps
                    in the transition block.
        dropout_rate: dropout rate
        weight_decay: weight decay factor
    Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
    '''
    concat_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(ip)
    x = Activation('relu')(x)
    x = Conv2D(int(nb_filter * compression), (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
               kernel_regularizer=l2(weight_decay))(x)
    x = AveragePooling2D((2, 2), strides=(2, 2))(x)

    return x 

def __transition_block(ip, nb_filter, compression=1.0, weight_decay=1e-4):
    ''' Apply BatchNorm, Relu 1x1, Conv2D, optional compression, dropout and Maxpooling2D
    Args:
        ip: keras tensor
        nb_filter: number of filters
        compression: calculated as 1 - reduction. Reduces the number of feature maps
                    in the transition block.
        dropout_rate: dropout rate
        weight_decay: weight decay factor
    Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
    '''
    concat_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(ip)
    x = Activation('relu')(x)
    x = Conv2D(int(nb_filter * compression), (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
               kernel_regularizer=l2(weight_decay))(x)
    x = AveragePooling2D((2, 2), strides=(2, 2))(x)

    # global context block
    x = global_context_block(x)

    return x 

def _build_image_embedding(self):
        image_model = InceptionV3(include_top=False, weights='imagenet',
                                  pooling='avg')
        for layer in image_model.layers:
            layer.trainable = False

        dense_input = BatchNormalization(axis=-1)(image_model.output)
        image_dense = Dense(units=self._embedding_size,
                            kernel_regularizer=self._regularizer,
                            kernel_initializer=self._initializer
                            )(dense_input)
        # Add timestep dimension
        image_embedding = RepeatVector(1)(image_dense)

        image_input = image_model.input
        return image_input, image_embedding 

def _build_sequence_model(self, sequence_input):
        RNN = GRU if self._rnn_type == 'gru' else LSTM

        def rnn():
            rnn = RNN(units=self._rnn_output_size,
                      return_sequences=True,
                      dropout=self._dropout_rate,
                      recurrent_dropout=self._dropout_rate,
                      kernel_regularizer=self._regularizer,
                      kernel_initializer=self._initializer,
                      implementation=2)
            rnn = Bidirectional(rnn) if self._bidirectional_rnn else rnn
            return rnn

        input_ = sequence_input
        for _ in range(self._rnn_layers):
            input_ = BatchNormalization(axis=-1)(input_)
            rnn_out = rnn()(input_)
            input_ = rnn_out
        time_dist_dense = TimeDistributed(Dense(units=self._vocab_size))(rnn_out)

        return time_dist_dense 

def transition_block(ip, nb_filter, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, Relu 1x1, Conv2D, optional dropout and Maxpooling2D

    Args:
        ip: keras tensor
        nb_filter: number of filters
        dropout_rate: dropout rate
        weight_decay: weight decay factor

    Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool

    '''

    concat_axis = 1 if K.image_dim_ordering() == "th" else -1

    x = Convolution2D(nb_filter, 1, 1, init="he_uniform", border_mode="same", bias=False,
                      W_regularizer=l2(weight_decay))(ip)
    if dropout_rate:
        x = Dropout(dropout_rate)(x)
    x = AveragePooling2D((2, 2), strides=(2, 2))(x)

    x = BatchNormalization(mode=0, axis=concat_axis, gamma_regularizer=l2(weight_decay),
                           beta_regularizer=l2(weight_decay))(x)

    return x 

def test_weight_init(self):
        """
        Test weight initialization
        """

        norm_m1 = normalization.BatchNormalization((10,), mode=1, weights=[np.ones(10),np.ones(10)])

        for inp in [self.input_1, self.input_2, self.input_3]:
            norm_m1.input = inp
            out = (norm_m1.get_output(train=True) - np.ones(10))/1.
            self.assertAlmostEqual(out.mean().eval(), 0.0)
            if inp.std() > 0.:
                self.assertAlmostEqual(out.std().eval(), 1.0, places=2)
            else:
                self.assertAlmostEqual(out.std().eval(), 0.0, places=2)

        assert_allclose(norm_m1.gamma.eval(),np.ones(10))
        assert_allclose(norm_m1.beta.eval(),np.ones(10))

        #Weights must be an iterable of gamma AND beta.
        self.assertRaises(Exception,normalization.BatchNormalization(10,), weights = np.ones(10)) 

def __transition_block(ip, nb_filter, compression=1.0, weight_decay=1e-4):
    ''' Apply BatchNorm, Relu 1x1, Conv2D, optional compression, dropout and Maxpooling2D
    Args:
        ip: keras tensor
        nb_filter: number of filters
        compression: calculated as 1 - reduction. Reduces the number of feature maps
                    in the transition block.
        dropout_rate: dropout rate
        weight_decay: weight decay factor
    Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
    '''
    concat_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(ip)
    x = Activation('relu')(x)
    x = Conv2D(int(nb_filter * compression), (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
               kernel_regularizer=l2(weight_decay))(x)
    x = AveragePooling2D((2, 2), strides=(2, 2))(x)

    return x 

def build_model():
    """
    定义模型
    """
    model = Sequential()

    model.add(LSTM(units=Conf.LAYERS[1], input_shape=(Conf.LAYERS[1], Conf.LAYERS[0]), return_sequences=True))
    model.add(Dropout(0.2))

    model.add(LSTM(Conf.LAYERS[2], return_sequences=False))
    model.add(Dropout(0.2))

    model.add(Dense(units=Conf.LAYERS[3]))
    # model.add(BatchNormalization(weights=None, epsilon=1e-06, momentum=0.9))
    model.add(Activation("tanh"))
    # act = PReLU(alpha_initializer='zeros', weights=None)
    # act = LeakyReLU(alpha=0.3)
    # model.add(act)

    start = time.time()
    model.compile(loss="mse", optimizer="rmsprop")
    print("> Compilation Time : ", time.time() - start)
    return model 

def conv_block(input, base, k=1, dropout=0.0):
    init = input

    channel_axis = 1 if K.image_data_format() == "channels_first" else -1

    x = BatchNormalization(axis=channel_axis, momentum=0.1, epsilon=1e-5, gamma_initializer='uniform')(input)
    x = Activation('relu')(x)
    x = Convolution2D(base * k, (3, 3), padding='same', kernel_initializer='he_normal',
                      use_bias=False)(x)

    if dropout > 0.0: x = Dropout(dropout)(x)

    x = BatchNormalization(axis=channel_axis, momentum=0.1, epsilon=1e-5, gamma_initializer='uniform')(x)
    x = Activation('relu')(x)
    x = Convolution2D(base * k, (3, 3), padding='same', kernel_initializer='he_normal',
                      use_bias=False)(x)

    m = Add()([init, x])
    return m 

def build_model():
    """
    定义模型
    """
    model = Sequential()

    model.add(LSTM(units=Conf.LAYERS[1], input_shape=(Conf.LAYERS[1], Conf.LAYERS[0]), return_sequences=True))
    model.add(Dropout(0.2))

    model.add(LSTM(Conf.LAYERS[2], return_sequences=False))
    model.add(Dropout(0.2))

    model.add(Dense(units=Conf.LAYERS[3]))
    # model.add(BatchNormalization(weights=None, epsilon=1e-06, momentum=0.9))
    model.add(Activation("tanh"))
    # act = PReLU(alpha_initializer='zeros', weights=None)
    # act = LeakyReLU(alpha=0.3)
    # model.add(act)

    start = time.time()
    model.compile(loss="mse", optimizer="rmsprop")
    print("> Compilation Time : ", time.time() - start)
    return model 

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 identity_block(input_tensor, filters, d_rates):
    x = Conv2D(filters[0], kernel_size=1, dilation_rate=d_rates[0])(input_tensor)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[1], kernel_size=3, padding='same', dilation_rate=d_rates[1])(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Conv2D(filters[2], kernel_size=1, dilation_rate=d_rates[2])(x)
    x = BatchNormalization()(x)

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

    return x 

def mlp_v2():
    model = Sequential()
    model.add(Dense(2048, input_shape=(21099,)))
    model.add(Activation('relu'))
    model.add(Dropout(0.5))
    model.add(BatchNormalization())
#     model.add(Dense(1024))
#     model.add(Activation('relu'))
#     model.add(Dropout(0.5))   
#     model.add(BatchNormalization())
    model.add(Dense(512))
    model.add(Activation('relu'))
    model.add(Dropout(0.5))   
    model.add(BatchNormalization())
    model.add(Dense(128))
    model.add(Activation('relu'))
    model.add(Dropout(0.5))    
    model.add(BatchNormalization())
    model.add(Dense(6))
    model.add(Activation('softmax'))

    model.compile(loss='categorical_crossentropy',
                  optimizer='nadam',
                  metrics=['accuracy'])
    return model 

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 mlp_v3():
    model = Sequential()
    model.add(Dense(1024, input_shape=(10102,)))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))

    model.add(Dense(256))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))   
 #   model.add(BatchNormalization())
    model.add(Dense(128))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))    
#    model.add(BatchNormalization())
#
    model.add(Dense(6))
    model.add(Activation('softmax'))

    model.compile(loss='categorical_crossentropy',
                  optimizer='Nadam',
                  metrics=['accuracy'])
    return model 

def mlp_v3():
    model = Sequential()
    model.add(Dense(1024, input_shape=(13,400,)))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))

    model.add(Dense(256))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))   
 #   model.add(BatchNormalization())
    model.add(Dense(128))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))    
#    model.add(BatchNormalization())
#
    model.add(Dense(6))
    model.add(Activation('softmax'))

    model.compile(loss='categorical_crossentropy',
                  optimizer='Nadam',
                  metrics=['accuracy'])
    return model 

def DarknetConv2D_BN_Leaky(*args, **kwargs):
    """Darknet Convolution2D followed by BatchNormalization and LeakyReLU."""
    no_bias_kwargs = {'use_bias': False}
    no_bias_kwargs.update(kwargs)
    return compose(
        DarknetConv2D(*args, **no_bias_kwargs),
        BatchNormalization(),
        LeakyReLU(alpha=0.1)) 

def DarknetConv2D(*args, **kwargs):
    darknet_conv_kwargs = {'kernel_regularizer': l2(5e-4)}
    darknet_conv_kwargs['padding'] = 'valid' if kwargs.get('strides')==(2,2) else 'same'
    darknet_conv_kwargs.update(kwargs)
    return Conv2D(*args, **darknet_conv_kwargs)

#---------------------------------------------------#
#   卷积块
#   DarknetConv2D + BatchNormalization + LeakyReLU
#---------------------------------------------------# 

def DarknetConv2D_BN_Leaky(*args, **kwargs):
    """Darknet Convolution2D followed by BatchNormalization and LeakyReLU."""
    no_bias_kwargs = {'use_bias': False}
    no_bias_kwargs.update(kwargs)
    return compose(
        DarknetConv2D(*args, **no_bias_kwargs),
        BatchNormalization(),
        LeakyReLU(alpha=0.1)) 

def BatchNorm(mode=2, axis=1, **kwargs):
    """Convenience method for BatchNormalization layers."""
    if KERAS_2:
        return BatchNormalization(axis=axis, **kwargs)
    else:
        return BatchNormalization(mode=2,axis=axis, **kwargs)