Junlei Zhang
Junlei Zhang
Hi, Thank you for your code. But I am confused about the "i" implemented in your code. I think it may be different from what you said in your paper....
Hello, thanks for your excellent code! Can this code training the just the word detector part correctly?
Hello, tThank you for your contribution. Howeverm I notice that all mbart models exceed 2GB. Do you have any plan to fix this issue?
@[yehuitang](https://github.com/yehuitang) Hello, thank you for releasing your VITAUG code. In your paper, you said you trained following the DEIT. DEIT used self-distillation during training. But I do not find it...
Thank you very much for your released code for VIG. I spent some time on reading your code carefully. But I am confused about some parts of code, could you...
Hello, I tired to reproduce your vit-B results on imagenet-1k. I run the scripts following your readme.md, except that I used one NVIDIA-A100 GPUs *8 instead two nodes. CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python...
The mbart model is implemented by hugging face
Hello: I noticed that the acc would drop after the decreasing epoch. I trained your baseline model and grafting model with the same cosine learning rate. The acc for the...
![image](https://user-images.githubusercontent.com/26025961/77132458-8a898e80-6a9a-11ea-9782-4398f851b752.png I trained the resnet32 on cifar100 with 2 grafting setting. I set the seed 1 for the first model and 2 for the second. But I found the acc...
Hello, do I have to install the cuda 11.0 for your package? Currently, my cuda version is 10.1, pytorch version is 1.5 and cudnn version is 0.6. But I can...