JackieWu

Hi, I wrote a project, which gives a way to add `AttSampler` without recompiling MXNet. https://github.com/wkcn/AttentionSampler

Thanks for your attention to our work! The error is `loss = criterion(outputs, outputs_teacher). RuntimeError: Expected object of scalar type Long but got scalar type Float for argument`. `torch.nn.CrossEntropyLoss()` does...

I have fixed the bug. Please update the code to the latest version. Thank you!

Close the issue. Feel free to re-open it if any problem exists : )

Thanks for your attention to our work! Sorry for the late reply. We have uploaded the teacher logits files, which were generated by CLIP-ViT-Large/14-22k on ImageNet-22k [(Ref. the tutorial)](https://github.com/microsoft/Cream/blob/main/TinyViT/docs/SAVE_TEACHER_LOGITS.md). You...

Close it. Feel free to re-open it if necessary for extending the date : )

> Could you please extend the date？ Thanks a lot ! Hi @HaoWuSR , the date has been extended.

Hi @sanyalsunny111 , sorry that I did not prepare the teacher logits on ImageNet-1k for this codebase. You can follow the [tutorial](https://github.com/microsoft/Cream/blob/main/TinyViT/docs/SAVE_TEACHER_LOGITS.md) to save the sparse logits.

Hi @sanyalsunny111, the following command is used to save sparse logits of CLIP-ViT-Large/14-22k on ImageNet-1k. ```bash python -m torch.distributed.launch --nproc_per_node 8 save_logits.py --cfg configs/teacher/clip_vit_large_patch14_22k.yaml --data-path ./ImageNet --batch-size 128 --eval --resume...

Hi @sanyalsunny111, you can try this script: ```bash python -m torch.distributed.launch --nproc_per_node 8 main.py --cfg configs/1k/tiny_vit_21m.yaml --data-path ./ImageNet --batch-size 128 --opts DISTILL.TEACHER_LOGITS_PATH ./teacher_logits_1k AUG.MIXUP 0.8 AUG.CUTMIX 1.0 DATA.DATASET imagenet TRAIN.EPOCHS...