-
Hello, thank you very much for your excellent work.
I can not find "from deit.datasets import get_post_process".Where is the code of "get_post_process"?
-
Hi, sorry to bother you. Why are the two special [CLS]tokens in DeiT said to be average as a single [CLS] token in the paper, but in the code I see that they are indeed cat together, what am I missing…
-
I've trained the upernet_deit-s16_512x512_80k_ade20k model but it has only reached a final mIoU of 0.2 compared to the 0.4296 value reported in the model zoo. When running the same evaluation script b…
-
There was a sentence on the project page that went, "Implementation based on [DeiT](https://arxiv.org/abs/2012.12877) pretrained on ImageNet-1K with distillation fine-tuning will be released soon". It…
-
May I ask which backbone you use to train cityscpes for semantic segmentation tasks
-
ValueError: Unrecognized model in ../SentiLARE. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: fnet, gptj, layoutlmv2, beit, rembert, visual_be…
-
Hi
Thanks for your outstanding work.
I faced an issue when I wanted to load one of the pretrained vit base with this URL: 'https://dl.fbaipublicfiles.com/deit/deit_base_patch16_224-b5f2ef4d.pth'…
-
Hi. thanks for your great job.
I trained deit-base with your QAT method using quant_train.py.
while training, it showed good eval TOP1 accuracy over 82 in early epoches.
but when I load the sav…
-
Great work! It is very interesting to handle ViT compression from the perspective of low-frequency components.
I feel a little confused about the attention score (Eq. 8). The definition looks ob…
-
It's important that we have a strong presence on the main website sot that anyone visiting there feels welcome.
Some of the places we should add content :
* The Team page (brief purpose state…