paddle复现pytorch踩坑(五）：dygraph的一些用法示例-CSDN博客

1. Conv2D

# paddlepaddle code
self.p_conv = Conv2D(inc, 2*kernel_size*kernel_size, filter_size=3, padding=1, stride=stride)
self.p_conv.weight = fluid.initializer.ConstantInitializer(value=0)

    1
    2
    3

报错：

assignment to parameter 'weight' should be of type Parameter or None, but got 'ConstantInitializer'

    1

改为

# paddlepaddle code
self.p_conv = Conv2D(inc, 2*kernel_size*kernel_size, filter_size=3, padding=1, stride=stride, param_attr=fluid.initializer.ConstantInitializer(value=0))

————————————————
版权声明：本文为CSDN博主「潜沉10」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/qq_32097577/article/details/112384842