Efficient-Transformer icon indicating copy to clipboard operation
Efficient-Transformer copied to clipboard

Online !!! Application of an efficient transformer improved based on Swin transformer on remote sensing segmentation

Results 9 Efficient-Transformer issues
Sort by recently updated
recently updated
newest added

Hi there! I am interested in your work. Your work is also brilliant. I have a question about the results you provided in the article in Table 11. When you...

i want to build an application which can predict `single picture`, where should i modify in`test.py`; another question is can i use `CPU` to run `test.py`

Hi, @zyxu1996 . I met a problem that the model and loaded state dict do not match exactly. Do you know why this happened? Thank you very much. ![image](https://user-images.githubusercontent.com/39206462/180406680-3cc471f0-7340-413a-9100-b8a1b76f4ae5.png)

The resultant image changes with different batchsizes, why? )

Hi, your test code is a multi-GPU test, but I'm using a single GPU for training, how can I change the test code? I ask you to help me.

"Hello, I'm studying your code and have a few questions. I apologize for the interruption, but could you please explain the following to me? In the train.py file, do setting...

Hello, I would like to do a separate study on your proposed Efficient_T backbone, but the code for this backbone is not found in the code, did you change it...

In your paper, Table 10 shows that models like FCN, Unet, and DANet did not achieve the results as presented in the table, even after training and testing them twice....

hello,i want to ask that I set multi-gpu training to single-gpu training,But report the following error: ![image](https://user-images.githubusercontent.com/86956907/223056395-0eebe57f-0f04-484d-8acb-11a7b28ce717.png) and I set it like this in the source code: ![image](https://user-images.githubusercontent.com/86956907/223056550-4eca486f-3439-4285-b995-b57ac0c91748.png) ![image](https://user-images.githubusercontent.com/86956907/223056590-1c9d5d85-21b9-4edd-a6f5-4a88fb477e7a.png)