-
Hi, @charlesCXK ,
Great work and thanks for the share of the code.
I have a question that the cps loss in the paper is also computed on the labeled data, but can't find in the code. Is it forgot …
-
I'm trying to implement mixup and `cutmix `augmentation in `matterport/maskrcnn` network which is mainly allows augmentation of this library. I've tried out some cool library with it, however, jut to …
innat updated
3 years ago
-
Could you kindly please give the training scripts for training CaiT-M48 distilled 448? Thanks.
-
我在使用 tu.dataset.MixupDataset 这个类时报错： AttributeError: 'MixupDataset' object has no attribute 'mixup_to_cutmix'。然后我看了一下源码，发现 MixupDataset 这里面没有 self.mixup_to_cutmix 这个属性， 而是只在参数上有 mixup_to_cutmix。
我想问一…
-
您好，我想问一下，为何我使用FP16训练的情况下无法使用MIxUp？是我配置文件的问题吗，可否给出一个可以在FP16下运行Mixup的源文件示例
-
I have wrote a code from your paper, and tried to reimplement the results on ImageNet, but I can't get a good result. I just get the baseline via your training strategy. But one thing, I have not cons…
-
## 論文URL
https://arxiv.org/abs/2201.03545
## 著者
Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie
## 会議
2022/1/16時点でarxivのみ
## 背景
- 2020年のV…
-
Hey @lhoyer ,
I had a small query about using `ema_model` for exp id: `212`. We are using it during training the model for unsupervised semantic segmentation part, where we use it to generate pseu…
-
When using a horizon > 1
```
X,y = SlidingWindowPanel(window_len=72,
unique_id_cols=['cohort'],
stride=1,
start=0,…
-
In the Data Augmentation example, pls tell that what exactly format is the `dataset`, as the first parameter of `tu.dataset.MixupDataset`
```python
train_transform = albumentations.Compose([
…