我正在使用keras构建一个用于图像分割的卷积神经网络,我想使用“反射填充”而不是填充“相同”,但我找不到在keras中这样做的方法。
inputs = Input((num_channels, img_rows, img_cols))
conv1=Conv2D(32,3,padding='same',kernel_initializer='he_uniform',data_format='channels_first')(inputs)有没有一种方法可以实现反射层并将其插入到keras模型中?
发布于 2018-06-04 19:27:05
找到解决方案了!我们只需要创建一个以层作为输入的新类,并使用tensorflow预定义函数来完成它。
import tensorflow as tf
from keras.engine.topology import Layer
from keras.engine import InputSpec
class ReflectionPadding2D(Layer):
def __init__(self, padding=(1, 1), **kwargs):
self.padding = tuple(padding)
self.input_spec = [InputSpec(ndim=4)]
super(ReflectionPadding2D, self).__init__(**kwargs)
def get_output_shape_for(self, s):
""" If you are using "channels_last" configuration"""
return (s[0], s[1] + 2 * self.padding[0], s[2] + 2 * self.padding[1], s[3])
def call(self, x, mask=None):
w_pad,h_pad = self.padding
return tf.pad(x, [[0,0], [h_pad,h_pad], [w_pad,w_pad], [0,0] ], 'REFLECT')
# a little Demo
inputs = Input((img_rows, img_cols, num_channels))
padded_inputs= ReflectionPadding2D(padding=(1,1))(inputs)
conv1 = Conv2D(32, 3, padding='valid', kernel_initializer='he_uniform',
data_format='channels_last')(padded_inputs)发布于 2018-11-17 17:41:34
上面接受的答案在当前的Keras版本中不起作用。以下是正在运行的版本:
class ReflectionPadding2D(Layer):
def __init__(self, padding=(1, 1), **kwargs):
self.padding = tuple(padding)
self.input_spec = [InputSpec(ndim=4)]
super(ReflectionPadding2D, self).__init__(**kwargs)
def compute_output_shape(self, s):
""" If you are using "channels_last" configuration"""
return (s[0], s[1] + 2 * self.padding[0], s[2] + 2 * self.padding[1], s[3])
def call(self, x, mask=None):
w_pad,h_pad = self.padding
return tf.pad(x, [[0,0], [h_pad,h_pad], [w_pad,w_pad], [0,0] ], 'REFLECT')发布于 2018-08-25 01:51:34
import tensorflow as tf
from keras.layers import Lambda
inp_padded = Lambda(lambda x: tf.pad(x, [[0,0], [27,27], [27,27], [0,0]], 'REFLECT'))(inp)Akihiko的解决方案不适用于新的keras版本,因此我提出了自己的解决方案。该代码段将一批202x202x3图像填充到256x256x3
https://stackoverflow.com/questions/50677544
复制相似问题