Sangdoo Yun

1. The script for ResNet50 on ImageNet is in [README](https://github.com/clovaai/CutMix-PyTorch/blob/master/README.md). Same as for ResNet101 on Imagnet training. ``` python train.py \ --net_type resnet \ --dataset imagenet \ --batch_size 256 \...

This repo does not have downstream training/testing code. The instructions to train/test on downstream tasks are described in our paper.

@Eldad27 Unfortunately, we don't have any plan to train and provide object detection models using CutMix now. Currently, only the ImageNet-pretrained models are available which can be fine-tuned for downstream...

> Or is the above mentioned scenario is purely an example? and you replace portions of images randomly? Yes it is done randomly.

> So there are chances that the main features (like head) of a dog won't be replaced right? Which in turn means paying attention to non significant parts of the...

@kapness Thank you for the kind reply! I followed your issue but the results were still worse than my expectation. It would be very helpful if you share your config...

@kapness Thank you for your advice. I will try it right now!

@kapness @JingChaoLiu Thank you for your kind replies. I trained vanilla Mask-RCNN on ICDAR2017-MLT and got F-score only 62% which is still far under the baseline. My settings: - based...

@kapness I checked the crop function with some visualization. It seems ok..

@hiyyg @rwightman Thank you for having interests in our ReLabel-ImageNet work. Indeed, I have conducted our `ReLabel` technic on this repository (`timm`) with `EfficientNet` variants, and their results are like...