-
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'…
-
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…
-
Hiiie the work is fantastic
Was trying my hands on distillation using your code
Did following till now and need your guidance to move forward pls
1. I have used the pretrained model given at the li…
-
## 🐛 Bug
Assume you want to load a model using torch.hub. For instance:
`torch.hub.list('githubaddress', 'model', pretrained=True)`
Now assume in your own project you have a package named 'mod…
-
Hi,
i want to use cosub trainging method for custom images classification work, but i don't find implemention in the code. Does this work contains the details of cosub training method. If yes, my com…
-
I am reproducing your results following the training instruction i.e using the command: CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
python _ET_pp_main_deitS.py\
--tag /deit_S \
--e…
-
Hi, for anyone who interested in the implementation of LayoutLMv3. Transfomers have updated the code for mask image modeling and the code is based on DEIT. You can inherit the code to implement the Ma…
-
Dear @kevin-ssy
How we can utilize TransMix for CIFAR-10 dataset? I have to conduct some experiments on CIFAR-10 dataset
-
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…
-
https://weiren1998.github.io/archives/697052e2.html#more
在探索网络架构的过程中,需要做很多尝试和思考,同时也需要把实验数据和对于结果的思考等记录下来,从而一点点积累感觉
最近在做本科的毕业设计,题目是足球视频中的行为关键帧检测算法设计。在实验过程中,发现有很多细小的想法,但有时一晃而过,可能是一些小的尝试,但很少会做对比试验…