-
### Branch/Tag/Commit
main
### Docker Image Version
nvcr.io/nvidia/pytorch:21.11-py3
### GPU name
V100
### CUDA Driver
cuda 11.5
### Reproduced Steps
```shell
1. cd $WORKSP…
-
Are the parameters of swinTransformer trained during fine-tuning?
-
In this issue-branch, the tail network for precipitation downscaling will be developed.
The IMERG dataset, reprojected onto a 0.083°-grid, will serve as the target data for this downscaling task.
Wh…
-
1. PaddleClas版本以及PaddlePaddle版本:如PaddleClas release/2.4和paddlepaddle-gpu 2.4.1.post112
2. 涉及的其他产品使用的版本号:无
3. 训练环境信息:
a. 具体操作系统,如Linux
b. Python版本号,如Python3.9
c. CUDA/cuDNN版本,…
-
We decided to use Swin Transformer, which shows SOTA performance on computer vision tasks including object detection / semantic segmentation, as a baseline of our project.
Here are the provided cod…
-
https://github.com/SwinTransformer/Swin-Transformer-Semantic-Segmentation
https://github.com/open-mmlab/mmsegmentation
-
I got {'BLEU': [0.8164844125702885, 0.6596750046143284, 0.5145357003585111, 0.3929742875865025], 'METEOR': 0.2901561761368199, 'ROUGE': 0.5838811960462188, 'CIDEr': 1.3468707161094793} with you provid…
-
Hi, does the SwinTransformer v2 do SimMiM pretraining? This is shown in the paper:
https://arxiv.org/pdf/2111.09883.pdf
If not, any plans to add/how difficult would it be to port?
-
Hello, this error occurred when I wanted to train the model. How can I download this pth file?
/home/jinw/anaconda3/envs/KVQ/lib/python3.8/site-packages/torch/functional.py:504: UserWarning: torc…
ads2d updated
3 months ago
-
大佬您好,我自己根据SwinTransformer源码将YOLOV5的6.1版本的backbone全部按SwinTransformer结构修改,遇到的半精度训练报错问题看您的train文件添加了'--nohalf'参数后成功了,但是我的GFLOPs很大,光depth_multiple: 0.33,width_multiple: 0.75的yolov5swin_tiny就409.9GFLOPs,而d…