-
### 論文へのリンク
[[arXiv:2001.04086] GridMask Data Augmentation](https://arxiv.org/abs/2001.04086)
### 著者・所属機関
Pengguang Chen, Shu Liu, Hengshuang Zhao, Jiaya Jia
### 投稿日時（YYYY-MM-DD）
- The …
-
hi@AlexeyAB
a new paper: https://arxiv.org/abs/2001.04086
It's very similar to cutout but different
-
hello @AlexeyAB @WongKinYiu ,
I have a training problem which it showed 0% map in the result.
I used three classes from the coco dataset which are frisbee, kite, baseball. I first trained with o…
-
When running `[petr_r50dcn_gridmask_p4.py](https://github.com/megvii-research/PETR/blob/main/projects/configs/petr/petr_r50dcn_gridmask_p4.py)`, the accuracy I got was:
mAP: 0.3022
mATE: 0.8507
mAS…
-
https://www.kaggle.com/ipythonx/keras-grapheme-gridmask-augmix-ensemble
Ensembling with Densenet 169 and EfficientNet B4
-
Hello
I want to remplace Randomerasing by Gridmask in the compse step
`def get_transform(resize, phase='train'):
if phase == 'train':
return transforms.Compose([
trans…
-
When i train the model on the mini or trainval dataset using the simple detr3d_resnet101_gridmask config , i get around 0 map and 0 nds in the end, the model does not learn anything as the training p…
-
我在petr_r50dcn_gridmask_p4.py 将img_backbone换成了resnext/darknet 但是不管我把学习率调的多小 训练过程中打印的grad_norm都是nan是怎么回事呢 有没有什么解决办法呢
-
Hi, thank you for your open source code. Where is the core code of GridMask and how can it be used on your own data set?
-
## Background
- mmsegmentation 에 존재하지 않은 여러 가지 augmentation 을 구현
## ToDo
- [x] Gridmask
- [ ] Mixup
- [ ] Cutmix