Animesh Gupta

Gradmatch Data subset selection method making training slow

9

I tried to run some experiments as follows: - Ran full cifar10 without any subset selection method to train resnet50 which took around 32m 31s. - Ran Gradmatch cifar10 subset...

There is no train.pickle file. I tried to use `src/prepare_dataset.py` for generating respective file but it's taking a lot of time. Can anyone suggest to me how to generate it?

Hi @HayeonLee . How we can use this codebase with the resnet50 network? Also, can you share the details on how we can create the dataset?

I am currently working with high resolution dataset. I am facing the following error. `Unable to join threads to shut down before fork(). This can break multithreading in child processes.`....

Here in the if condition [code](https://github.com/jeonsworld/ViT-pytorch/blob/main/train.py#L206), is check for (step+1) == len(trainset) missing? Reference --> [Reference code](https://kozodoi.me/python/deep%20learning/pytorch/tutorial/2021/02/19/gradient-accumulation.html)

Dark mode gets switched off after refreshing the page

5

#### I am submitting a - * [] **Feature Request** * [x] **Bug Report** #### Describe your bug/feature - Dark mode gets switched off after refreshing the page rather it...

How to integrate Adaptive Gradmatch in the existing codebase?

1

Hi. Thank you for the great work. I wanted to ask, is there a way where I can use adaptive gradmatch in the codebase? If not, can you guide me...

[Feature Request] A switch command to add data continuously when switch is on

1

As suggested with @daemon1024. Idea ``` /saveurl on From here on whatever URLs are shared the links are kept in the database. Yeah will need to clean up things regularly,...

Hi @tinymilky, could you please update the repository with the code to reproduce the results on AbodmenCT?