python类AveragePooling2D()的实例源码

densenet.py 文件源码 项目:DenseNet 作者: titu1994 项目源码 文件源码 阅读 27 收藏 0 点赞 0 评论 0
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
densenet_fast.py 文件源码 项目:DenseNet 作者: titu1994 项目源码 文件源码 阅读 19 收藏 0 点赞 0 评论 0
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
resnet.py 文件源码 项目:convnet-study 作者: robertomest 项目源码 文件源码 阅读 24 收藏 0 点赞 0 评论 0
def downsample_block(x, nb_channels, kernel_size=3, bottleneck=True,
                     l2_reg=1e-4):
    if bottleneck:
        out = bottleneck_layer(x, nb_channels, kernel_size=kernel_size,
                               stride=2, l2_reg=l2_reg)
        # The output channels is 4x bigger on this case
        nb_channels = nb_channels * 4
    else:
        out = two_conv_layer(x, nb_channels, kernel_size=kernel_size,
                             stride=2, l2_reg=l2_reg)
    # Projection on the shortcut
    proj = Convolution2D(nb_channels, 1, 1, subsample=(2, 2),
                         border_mode='valid', init='he_normal',
                         W_regularizer=l2(l2_reg), bias=False)(x)
    # proj = AveragePooling2D((1, 1), (2, 2))(x)
    out = merge([proj, out], mode='sum')
    return out
densenet_fc.py 文件源码 项目:Fully-Connected-DenseNets-Semantic-Segmentation 作者: titu1994 项目源码 文件源码 阅读 19 收藏 0 点赞 0 评论 0
def __transition_block(ip, nb_filter, compression=1.0, dropout_rate=None, 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_dim_ordering() == "th" else -1

    x = BatchNormalization(mode=0, axis=concat_axis, gamma_regularizer=l2(weight_decay),
                           beta_regularizer=l2(weight_decay))(ip)
    x = Activation('relu')(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, init="he_uniform", border_mode="same", bias=False,
                      W_regularizer=l2(weight_decay))(x)
    if dropout_rate:
        x = Dropout(dropout_rate)(x)
    x = AveragePooling2D((2, 2), strides=(2, 2))(x)

    return x
model.py 文件源码 项目:DeepWorks 作者: daigo0927 项目源码 文件源码 阅读 20 收藏 0 点赞 0 评论 0
def build(input_shape, num_outputs,
              block_fn, repetitions):

        inputs = Input(shape = input_shape)
        conv1 = Conv2D(64, (7, 7), strides = (2, 2),
                       padding = 'same')(inputs)
        conv1 = BatchNormalization()(conv1)
        conv1 = Activation('relu')(conv1)
        pool1 = MaxPooling2D(pool_size = (3, 3), strides = (2, 2),
                            padding = 'same')(conv1)

        x = pool1
        filters = 64
        first_layer = True
        for i, r in enumerate(repetitions):
            x = _residual_block(block_fn, filters = filters,
                                repetitions = r, is_first_layer = first_layer)(x)
            filters *= 2
            if first_layer:
                first_layer = False

        # last activation <- unnecessary???
        # x = BatchNormalization()(x)
        # x = Activation('relu')(x)

        _, w, h, ch = K.int_shape(x)
        pool2 = AveragePooling2D(pool_size = (w, h), strides = (1, 1))(x)
        flat1 = Flatten()(pool2)
        outputs = Dense(num_outputs, kernel_initializer = init,
                        activation = 'softmax')(flat1)

        model = Model(inputs = inputs, outputs = outputs)
        return model
get_final_test_dense121_feature.py 文件源码 项目:Baidu-_contest 作者: DeepLJH0001 项目源码 文件源码 阅读 30 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage)

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
get_final_test_inceptionv4_feature.py 文件源码 项目:Baidu-_contest 作者: DeepLJH0001 项目源码 文件源码 阅读 20 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage)

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
a01_densenet_161.py 文件源码 项目:KAGGLE_CERVICAL_CANCER_2017 作者: ZFTurbo 项目源码 文件源码 阅读 21 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage)

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
a01_densenet_121.py 文件源码 项目:KAGGLE_CERVICAL_CANCER_2017 作者: ZFTurbo 项目源码 文件源码 阅读 23 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage)

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
visualization.py 文件源码 项目:Aesthetic_attributes_maps 作者: gautamMalu 项目源码 文件源码 阅读 21 收藏 0 点赞 0 评论 0
def get_features(image, model):
    '''
    get the feature map of all activation layer for given
    image and given model
    :param image: input image path
    :param model: given model
    :return: all activation layers features
    '''

   # image = load_image(image_src)
    feature_maps = np.zeros((10, 10, 15104))
    activation_layers = ['activation_' + str(i) for i in range(4, 50, 3)]
    start_index = 0

    for i, layer_name in enumerate(activation_layers):
        layer = model.get_layer(layer_name)
        nchannel = layer.output_shape[-1]
        conv_output = layer.output
    # Adujusting pooling size with respect to input layers` size
        if layer.output_shape[-2] == 74:
            conv_output = AveragePooling2D(pool_size=(7, 7))(conv_output)
        if layer.output_shape[-2] == 37:
            conv_output = AveragePooling2D(pool_size=(4, 4), border_mode='same')(conv_output)
        if layer.output_shape[-2] == 19:
            conv_output = AveragePooling2D(pool_size=(2, 2), border_mode='same')(conv_output)

        featuremap_function = K.function([model.input, K.learning_phase()], [conv_output])

        output = featuremap_function([image, 0])
        feature_maps[:, :, start_index:start_index+nchannel] = output[0][0, :, :, :]

        start_index = start_index + nchannel

    return feature_maps
densenet169.py 文件源码 项目:cnn_finetune 作者: flyyufelix 项目源码 文件源码 阅读 23 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout 
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage) 

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
densenet161.py 文件源码 项目:cnn_finetune 作者: flyyufelix 项目源码 文件源码 阅读 25 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout 
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage) 

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
densenet121.py 文件源码 项目:cnn_finetune 作者: flyyufelix 项目源码 文件源码 阅读 25 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout 
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage) 

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
densenet.py 文件源码 项目:convnet-study 作者: robertomest 项目源码 文件源码 阅读 18 收藏 0 点赞 0 评论 0
def transition_block(x, nb_channels, dropout=0., l2_reg=1e-4):
    x = add_layer(x, nb_channels, kernel_size=1, dropout=dropout, l2_reg=l2_reg)
    # x = Convolution2D(n_channels, 1, 1, border_mode='same',
    #                   init='he_normal', W_regularizer=l2(l2_reg))(x)
    x = AveragePooling2D()(x)
    return x
densenet169.py 文件源码 项目:head-segmentation 作者: szywind 项目源码 文件源码 阅读 27 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage)

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
densenet161.py 文件源码 项目:head-segmentation 作者: szywind 项目源码 文件源码 阅读 24 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage)

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
densenet121.py 文件源码 项目:head-segmentation 作者: szywind 项目源码 文件源码 阅读 26 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout 
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage) 

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
densenetFCN.py 文件源码 项目:keras_zoo 作者: david-vazquez 项目源码 文件源码 阅读 16 收藏 0 点赞 0 评论 0
def transition_down(inputs, n_filters, compression=1.0, dropout=0.,
                    weight_decay=1e-4, name=''):
    n_filters = int(n_filters*compression)
    l = bn_relu_conv(inputs, n_filters, 1, dropout, name=name+'_TD')
    l = AveragePooling2D((2, 2), strides=(2, 2), name=name+'_TD_pool')(l)
    return l, n_filters


# Build the DenseNet model
densenet169.py 文件源码 项目:DenseNet-Keras 作者: flyyufelix 项目源码 文件源码 阅读 30 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout 
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage) 

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
densenet161.py 文件源码 项目:DenseNet-Keras 作者: flyyufelix 项目源码 文件源码 阅读 23 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout 
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage) 

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
densenet121.py 文件源码 项目:DenseNet-Keras 作者: flyyufelix 项目源码 文件源码 阅读 24 收藏 0 点赞 0 评论 0
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout 
        # Arguments
            x: input tensor
            stage: index for dense block
            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
    '''

    eps = 1.1e-5
    conv_name_base = 'conv' + str(stage) + '_blk'
    relu_name_base = 'relu' + str(stage) + '_blk'
    pool_name_base = 'pool' + str(stage) 

    x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
    x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
    x = Activation('relu', name=relu_name_base)(x)
    x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=False)(x)

    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)

    return x
wide_resnet.py 文件源码 项目:keras-contrib 作者: farizrahman4u 项目源码 文件源码 阅读 22 收藏 0 点赞 0 评论 0
def __create_wide_residual_network(nb_classes, img_input, include_top, depth=28, width=8, dropout=0.0):
    ''' Creates a Wide Residual Network with specified parameters

    Args:
        nb_classes: Number of output classes
        img_input: Input tensor or layer
        include_top: Flag to include the last dense layer
        depth: Depth of the network. Compute N = (n - 4) / 6.
               For a depth of 16, n = 16, N = (16 - 4) / 6 = 2
               For a depth of 28, n = 28, N = (28 - 4) / 6 = 4
               For a depth of 40, n = 40, N = (40 - 4) / 6 = 6
        width: Width of the network.
        dropout: Adds dropout if value is greater than 0.0

    Returns:a Keras Model
    '''

    N = (depth - 4) // 6

    x = __conv1_block(img_input)
    nb_conv = 4

    for i in range(N):
        x = __conv2_block(x, width, dropout)
        nb_conv += 2

    x = MaxPooling2D((2, 2))(x)

    for i in range(N):
        x = __conv3_block(x, width, dropout)
        nb_conv += 2

    x = MaxPooling2D((2, 2))(x)

    for i in range(N):
        x = ___conv4_block(x, width, dropout)
        nb_conv += 2

    x = AveragePooling2D((8, 8))(x)

    if include_top:
        x = Flatten()(x)
        x = Dense(nb_classes, activation='softmax')(x)

    return x


问题


面经


文章

微信
公众号

扫码关注公众号