-
First of all, I should point out that it's just a simple experiment for Swin-Transformer.
## Main Idea
As sliding window in Swin-Transformer tries to get correlation attention between different wi…
-
Hi,
I would like to test the instance segmentation model on a single image. Is it possible.
In test.py i dont see any input argument to test on our own images.
Here is the command i did
`python…
-
error as following:
raceback (most recent call last):
File "./train.py", line 188, in
main()
File "./train.py", line 162, in main
model.init_weights()
File "/home/liuguangcan/anac…
-
**Describe the bug**
when trying to train my model with customized dataset, there is an Assertion failed,
`cv2.error: OpenCV(4.1.2) /io/opencv/modules/core/src/copy.cpp:1170: error: (-215:Assertion …
-
When I am running the inference step, I meet the error as below.
![微信图片_20210414193900](https://user-images.githubusercontent.com/38532963/114704417-27c7fc80-9d59-11eb-9f5d-18351e859948.png)
…
-
Thanks for your work,but I encounter some problem when I trying to resume from latest training result.
**Describe the bug**
My computer lost power when training,I try to resume but I got a 'Permis…
-
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22kto1k.pth\
What does the models under the 1k model column in the ImageNet-22k pre-trained models m…
-
`python tools/train.py configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k.py --options model.pretrained=checkpoints/swin_tiny_patch4_window7_224.pth model.backbone.use_checkpoint=True -…
-
How about try this tech?
-
I have already tried tiny and small version, none of them can run.
When train without pretrained weight, it is works *fine*, but time is a problem.
The following is the configs :
```
model = dict(…