重新fork一个重新写呗

数据类型不对？

复现也失败了……

我觉得得把报错贴出来

ValueError: (InvalidArgument) The number of input's channels should be equal to filter's channels * groups for Op(Conv). But received: the input's channels is 224, the input's shape is [64, 224, 224, 3]; the filter's channels is 3, the filter's shape is [64, 3, 7, 7]; the groups is 1, the data_format is NCHW. The error may come from wrong data_format setting.
  [Hint: Expected input_channels == filter_dims[1] * groups, but received input_channels:224 != filter_dims[1] * groups:3.] (at /paddle/paddle/fluid/operators/conv_op.cc:96)
  [Hint: If you need C++ stacktraces for debugging, please set `FLAGS_call_stack_level=2`.]
  [operator < conv2d > error]

感觉像是shape不对……

数据喂入模型前打印下看看shape

transform输入输出形状也可以查查

问题后续：https://ai.baidu.com/forum/topic/show/981792

弄好了，就是时间久了点。

再去看看精品项目，看看抄个啥比较容易学会。

厉害了~~~