Zhipeng Huang
Zhipeng Huang
> Coremltools 6.2 [includes support for PyTorch's `fft_rfftn` op](https://github.com/apple/coremltools/blob/13b69cc9ae05bce830a922b2dbb66843635aa72b/coremltools/converters/mil/frontend/torch/ops.py#L5543-L5548). > > Thanks @junpeiz for adding that. Still cannot convert? 
> @hzphzp the PyTorch's `rfft2` is just a special case of `rfftn` (see https://pytorch.org/docs/stable/generated/torch.fft.rfft2.html), and it should be trivial to use `rfftn` to replace the `rfft2` in your model. If...
same problem
> @JackYansongLi @hzphzp Is it related to this? [#7243 (comment)](https://github.com/logseq/logseq/pull/7243#issuecomment-1325342553) Yes! Thank you for your help.
我是重度xmind用户，最近想要写一个多xmind文件，内容文本搜索和文件内图片ocr搜索的小工具，发现自己的xmind2020 文件都无法用官方的python sdk load。希望官方可以帮忙解决一下这个问题，谢谢。
> In the paper, FLOPs were reported at 224x224 input resolution. Are you using the same size? > > Regarding accuracy: EMA is useful for MobileViT models (as noted in...
Thank you for your reply, I found the bug is that I still use the "imagenet_opencv" as dataIO function.
Same question~
Same issue, it hangs when training with multi-gpus.