Cropping2D层
Cropping2D class
keras.layers.Cropping2D(cropping=((0, 0), (0, 0)), data_format=None, **kwargs)
裁剪层用于2D输入（例如图片）.
它沿着空间维度进行裁剪,即高度和宽度.
示例:
>>> input_shape = (2, 28, 28, 3)
>>> x = np.arange(np.prod(input_shape)).reshape(input_shape)
>>> y = keras.layers.Cropping2D(cropping=((2, 2), (4, 4)))(x)
>>> y.shape
(2, 24, 20, 3)
参数:
cropping: 整数,或2个整数的元组,或2个2个整数的元组.
- 如果为整数: 对高度和宽度应用相同的对称裁剪.
- 如果为2个整数的元组: 解释为高度和宽度的两个不同的对称裁剪值:
(对称高度裁剪, 对称宽度裁剪).
- 如果为2个2个整数的元组: 解释为
((顶部裁剪, 底部裁剪), (左侧裁剪, 右侧裁剪)).
data_format: 字符串,取值为"channels_last"（默认）或
"channels_first".输入中维度的顺序.
"channels_last"对应输入形状
(batch_size, height, width, channels),而"channels_first"
对应输入形状
(batch_size, channels, height, width).
如果未指定,使用在您的Keras配置文件~/.keras/keras.json中找到的image_data_format值（如果存在）.默认为
"channels_last".
输入形状:
4D张量,形状为:
- 如果data_format为"channels_last":
(batch_size, height, width, channels)
- 如果data_format为"channels_first":
(batch_size, channels, height, width)
输出形状:
4D张量,形状为:
- 如果data_format为"channels_last":
(batch_size, cropped_height, cropped_width, channels)
- 如果data_format为"channels_first":
(batch_size, channels, cropped_height, cropped_width)