kelisiya

> > I have sloved it. Some issues are : 1、noise = out.new_empty(b, 1, h, w).normal_() in stylegan2_clean_arch.py can‘t be supported in ONNX. I move it out the Model class,...

+1

> Hello, I would like to ask, why the test image I input is 1024 * 1024, but the output is indeed 256 * 256, and I did not see...

> > Did you use any data augmentation? > > Just same with the official code in the dataloader.py file, which including filp, rescale and crop. Regarding the rescale and...

> Thanks for your contribution. > Here are the code-comments in pointrend.py class: PointHead-inference: > """ > During inference, subdivision uses N=8096 > (i.e., the number of points in the...

+1

This problem looks like about GUPs, my computer have 2 gpus , but I can't use torch.distributed.launch. If I want to train the model , how to modify the code ? 

I found the error from docker . But I have a new question, why do I train the model has 302.7MB , but gca-dist is 101.3MB?

> @CDOTAD 这个matting确实挺难做的，几个指标的测试代码 有吗？能分享下吗？感谢 测试代码作者的Utils/Tester里有，计算MSE和SAD，由于测试集是1000张所以最终除以里1000

> 有人知道stage1 和 stage2 的训练周期多少比较合适吗？感谢感谢 请问一下你 TrainingSetPreparation.py 这个代码是如何跑通的？为何我使用之后就待机了，应该如何修改使它可以正常运行？