-
Hello,
I want to pretrain Point-BERT model on ModelNet40 , I trained ModelNet's dVAE model and configured .pkl weights in Point-BERT.yaml. When I run I get the following error, is this a problem with…
sw778 updated
2 years ago
-
Hi!
I have a question for the loss re-weighting.
According to my understanding, image with higher k should be assigned a lower loss weight since it is easier to predict with more information disclos…
-
欢迎您使用PaddleClas并反馈相关问题，非常感谢您对PaddleClas的贡献！
提出issue时，辛苦您提供以下信息，方便我们快速定位问题并及时有效地解决您的问题：
1. PaddleClas版本以及PaddlePaddle版本：PaddleClas 2.3 和PaddlePaddle 2.1.2
2. 涉及的其他产品使用的版本号：如您在使用PaddleClas的同时还在使用其他…
-
I encountered these errors when testing with ```SmoothCELoss``` and ```FocalLoss```, the logs are below:
1. ```Focal loss```
```python
[Errno 2] No such file or directory: 'main'
/content/main
…
-
Hi @ChunyuanLI, I've noticed the usage of mixup and cutmix during pre-training, which is not included in DINO. I'm wondering the performance gain brought by applying mixup & cutmix. Have you ever run …
-
There are some errors when I use your robustness toolbox. I need some help.
In my machine browser, https://drive.google.com can be accessed
source code:
```
from robustbench.utils import load_mode…
-
**Describe your feature request**
Check and modify the training settings for CrossViT models, add missing processing and training methods.
**Describe the reference code or paper**
- Paper link: h…
-
Hi,
I'm running your code for CIFAR-100 with Convit backbone (as suggested in the Readme file. I'm running into this error when the rehearsal memory is being updated.
```
/volumes1/Home/anaco…
-
Hi, Thank you for your excellent work. I have some questions concerning 3D configuration of GF-Net.
I extend your model to a 3D version by introducing 3D FFT and IFFT to conduct global filter learnin…
-
### 分支
master 分支 (0.24 或其他 0.x 版本)
### 描述该错误
# Config:
```python
model = dict(
type='ImageClassifier',
backbone=dict(
type='SwinTransformerV2',
arch='tiny',
i…