ShapeTextureDebiasedTraining
ShapeTextureDebiasedTraining copied to clipboard
LiYingwei
Code and models for the paper Shape-Texture Debiased Neural Network Training (ICLR 2021)
Hi, thank you for your nice work! I found that the labels of style for the original image are different w/ or w/o multi_grid. When deploying multi_grid, the label of...
Changes: - Eliminate Bar in utils and use the [progress ](https://pypi.org/project/progress/)package instead - Eliminate the global `state` variable, which was causing problems, and create relevant workarounds - Fix issue related...
Solving issues with the current version of PyTorch. **Changes Made:** Replaced transforms.RandomSizedCrop(224) with transforms.RandomResizedCrop(224) for random resizing and cropping of images. Deprecated the use of transforms.Scale and replaced it with...
Hi @LiYingwei In the paper under the section 2.2 EVALUATION AND OBSERVATION you mentioned that "all models are trained and evaluated on **ImageNet-200**". These images are downsized to 64×64 colored...
Hi @LiYingwei Thanks for the repo, and codes. I was reading the paper and had a look at the codes as well. Specially the [visualization ](https://github.com/LiYingwei/ShapeTextureDebiasedTraining/blob/master/utils/visualize.py) part. I was wondering...
