当前位置: 首页>>代码示例>>Python>>正文


Python layers.SeparableConv2D方法代码示例

本文整理汇总了Python中tensorflow.keras.layers.SeparableConv2D方法的典型用法代码示例。如果您正苦于以下问题:Python layers.SeparableConv2D方法的具体用法?Python layers.SeparableConv2D怎么用?Python layers.SeparableConv2D使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在tensorflow.keras.layers的用法示例。


在下文中一共展示了layers.SeparableConv2D方法的4个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: SeparableConvBlock

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import SeparableConv2D [as 别名]
def SeparableConvBlock(num_channels, kernel_size, strides, name, freeze_bn=False):
    f1 = layers.SeparableConv2D(num_channels, kernel_size=kernel_size, strides=strides, padding='same',
                                use_bias=True, name=f'{name}/conv')
    f2 = layers.BatchNormalization(momentum=MOMENTUM, epsilon=EPSILON, name=f'{name}/bn')
    # f2 = BatchNormalization(freeze=freeze_bn, name=f'{name}/bn')
    return reduce(lambda f, g: lambda *args, **kwargs: g(f(*args, **kwargs)), (f1, f2)) 
开发者ID:xuannianz,项目名称:EfficientDet,代码行数:8,代码来源:model.py

示例2: __init__

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import SeparableConv2D [as 别名]
def __init__(self, width, depth, num_anchors=9, separable_conv=True, freeze_bn=False, detect_quadrangle=False, **kwargs):
        super(BoxNet, self).__init__(**kwargs)
        self.width = width
        self.depth = depth
        self.num_anchors = num_anchors
        self.separable_conv = separable_conv
        self.detect_quadrangle = detect_quadrangle
        num_values = 9 if detect_quadrangle else 4
        options = {
            'kernel_size': 3,
            'strides': 1,
            'padding': 'same',
            'bias_initializer': 'zeros',
        }
        if separable_conv:
            kernel_initializer = {
                'depthwise_initializer': initializers.VarianceScaling(),
                'pointwise_initializer': initializers.VarianceScaling(),
            }
            options.update(kernel_initializer)
            self.convs = [layers.SeparableConv2D(filters=width, name=f'{self.name}/box-{i}', **options) for i in
                          range(depth)]
            self.head = layers.SeparableConv2D(filters=num_anchors * num_values,
                                               name=f'{self.name}/box-predict', **options)
        else:
            kernel_initializer = {
                'kernel_initializer': initializers.RandomNormal(mean=0.0, stddev=0.01, seed=None)
            }
            options.update(kernel_initializer)
            self.convs = [layers.Conv2D(filters=width, name=f'{self.name}/box-{i}', **options) for i in range(depth)]
            self.head = layers.Conv2D(filters=num_anchors * num_values, name=f'{self.name}/box-predict', **options)
        self.bns = [
            [layers.BatchNormalization(momentum=MOMENTUM, epsilon=EPSILON, name=f'{self.name}/box-{i}-bn-{j}') for j in
             range(3, 8)]
            for i in range(depth)]
        # self.bns = [[BatchNormalization(freeze=freeze_bn, name=f'{self.name}/box-{i}-bn-{j}') for j in range(3, 8)]
        #             for i in range(depth)]
        self.relu = layers.Lambda(lambda x: tf.nn.swish(x))
        self.reshape = layers.Reshape((-1, num_values))
        self.level = 0 
开发者ID:xuannianz,项目名称:EfficientDet,代码行数:42,代码来源:model.py

示例3: sep_conv

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import SeparableConv2D [as 别名]
def sep_conv(x, num_filters, kernel_size=(3, 3), activation='relu'):
    if activation == 'selu':
        x = layers.SeparableConv2D(num_filters, kernel_size,
                                   activation='selu',
                                   padding='same',
                                   kernel_initializer='lecun_normal')(x)
    elif activation == 'relu':
        x = layers.SeparableConv2D(num_filters, kernel_size,
                                   padding='same',
                                   use_bias=False)(x)
        x = layers.BatchNormalization()(x)
        x = layers.Activation('relu')(x)
    else:
        ValueError('Unknown activation function: %s' % (activation,))
    return x 
开发者ID:keras-team,项目名称:keras-tuner,代码行数:17,代码来源:xception.py

示例4: separableConv

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import SeparableConv2D [as 别名]
def separableConv(filters, kernel_size, strides=1, dilation_rate=1, use_bias=True):
    return layers.SeparableConv2D(filters, kernel_size, strides=strides, padding='same', use_bias=use_bias,
                                  depthwise_regularizer=regularizers.l2(l=0.0003),
                                  pointwise_regularizer=regularizers.l2(l=0.0003), dilation_rate=dilation_rate) 
开发者ID:1044197988,项目名称:TF.Keras-Commonly-used-models,代码行数:6,代码来源:MiniNetv2.py


注:本文中的tensorflow.keras.layers.SeparableConv2D方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。