-
**Describe the bug**
I'm trying to build a binary classifier and here's the error during first epoch's inference
```
Traceback (most recent call last):
File "train.py", line 798, in
main()…
-
你好，请问一下在数据增强部分的实验中，你们有试过mixup这个操作么。
-
In the paper [mixup: Beyond Empirical Risk Minimization](https://arxiv.org/abs/1710.09412), it seems that Mixup performs the best on ImageNet when the hyper-parameter alpha is between 0.2 and 0.4. For…
-
Hi,
Thank you for the sharing and excellent work. In order to reproduce the Tab2 results(w/o CutMix Aug) of ResNet101 on Cityscapes dataset, we just change the path of pretrain_model path in 'confi…
-
I am currently trying to build my own custom mask detector. I want to use CutMix as my data augmentation method, but when I use it, I get
```
cutmix=1 - isn't supported for Detector (use cutmix=1 o…
-
首先感谢贵团队的工作。
在[此页面](https://paddleclas.readthedocs.io/zh_CN/latest/advanced_tutorials/image_augmentation/ImageAugment.html#)展示了使用不同数据增强方法得到的实验结果。请问这些实验中数据增强的超参数（如Cutmix和Mixup中的alpha）设置是怎样的？是否就是[这里](ht…
-
Thanks for your error report and we appreciate it a lot.
**Checklist**
1. I have searched related issues but cannot get the expected help.
2. I have read the [FAQ documentation](https://mmdetec…
-
I am able to use mixup with cross entropy loss but not sure how it can be applied with center loss and triplet loss also?
In paper, mixup augmentation is not mentioned. any reason for not using it?
…
-
I follow the default setting of codes and obtained 71.687% mIoU when training with 1/8 labels on pascal voc，but this paper reported 73.67% mIoU. Why the performance gap so huge, and anyone can tell me…
-
Hello I have problem to run your code on CiFar10
i cannot find the function cutmix
`from cutmix.cutmix import CutMix
from cutmix.utils import CutMixCrossEntropyLoss`