-
In the paper you mention that flips are applied with 50 percent probability. Is it also the case that each randaugment sample is also applied with 50 percent probability or are two randaugment choices…
-
Many thanks for your clean codes.
(1) It seems there is no code of dataloader for SVHN dataset. Would you like to introduce what kinds of data pre-processing and augmenation methods (and mean&std …
-
It says that this repo contains the PyTorch implementation of the paper but there are no files here.
-
### Backbone
* EfficientNet
* https://github.com/zhanghang1989/ResNeSt
### Pre-trained model
* better pre-trained model than ImageNet-1.2M pre-trained model
- Weakly supervised Instagram-1G (…
-
Thanks for the great work, I need your help.
If I want to solve the three-category problem, which code should I modify. For example: if there are three categories in the BreastCancer dataset. Becau…
-
## 🚀 Feature
Inclusion of new Augmentation techniques in `torchvision.transforms`.
## Motivation
Transforms are important for data augmentation :sweat_smile:
## Proposals
- [x] [Ran…
-
Hi,
Thanks for the interesting work and sharing the code.
Recently, I reproduced the Fine-Tuning baseline method based on the released code for Self-Tuning method (directly delete the unlabeled …
-
大佬，非常感谢您分享这么好的工程。
请教一下您，您的代码中没有看到，强数据增强的代码？和相关的损失函数？大佬可否指点一下。
-
Hi
can you provide the commands (like you did in MixMatch repo, the runs/ folder) to reproduce the results in the paper?
Thanks a lot! and thanks for the great work!
-
I am running this code on a server that has a time limit of one day per job. So, I need to resume the code. I see a drop in accuracy when the training is resuming.
Could you please comment on what …