raven

Because the crop_size argument is disabled while testing. The argument is enabled while only training. Please refer https://github.com/fyu/drn/blob/d75db2ee7070426db7a9264ee61cf489f8cf178c/segment.py#L632-L640 and https://github.com/fyu/drn/blob/d75db2ee7070426db7a9264ee61cf489f8cf178c/segment.py#L360-L383

Thanks for your question. In the algorithm, we don't explicitly differentiate between open-set and close-set data. The discriminator implictly differentiates betweem them using their entropy.

1. The classifier shares a feature extractor with a discriminator, and the head consists of one fully-connected layer. We update the parameters of the classifier at the same time as...

Hi, would you please refer to Appendix B. Datasets. In a section of deepfashion, the authors describe "we first get its segmentation map, then re-organize the map into eight categories:...

The authors describe 4 important hyper parameters in 4.1: Number of prefix positions and suffix positions exists via `loc` parameters. I borrow the pyreft implementation for parsing the positions. As...

Sorry, I took the wrong operation, which fork sync with discards my commits, closing this pull request. Can I reopen it?

I think the code is ready for the review.

Thank you for the feedback. My code does not depend on `pyvene` and works with just integrating few codes in `pyreft` and `pyvene`. I think ReFT mainly consists of the...

@frankaging Thank you for the feedback. One of the motivations for integrating ReFT into the PEFT library is to allow ReFT to support more architectures. IIUC, although PEFT support any...

I faced same error. After installing ninja with `pip install ninja`, it was solved.