steven5401

@peterneher I reference your code, and facing same problem. Though I change loading method like [https://caffe2.ai/docs/tutorial-loading-pre-trained-models.html](https://caffe2.ai/docs/tutorial-loading-pre-trained-models.html), it still can work. Have you found the solution yet?

@lhCheung1991 please refer this post [https://github.com/caffe2/caffe2/issues/884](https://github.com/caffe2/caffe2/issues/884) I have found answer in last comment.

You should save extra parameter with _rm and _riv in init_net, predict_net in your save fuction. It is no need to change loading function.

I use nearest neighbor to downsample GT. This workaround can successfully back propagate. However, I don't think that single left-top pixel can represent 8x8 patch in original size GT.

我的目錄是D:\Downloads\PoeCharm_v20211027