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

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Results 196 Swin-Transformer issues
Sort by recently updated
recently updated
newest added

Hi and thanks for open-sourcing all these models. I am trying to replicate the performance reported for SWIN-L on ADE20K and I found multiple Imagenet22k checkpoints. Can you please share...

if (idx + 1) % config.TRAIN.ACCUMULATION_STEPS == 0: optimizer.step() optimizer.zero_grad() lr_scheduler.step_update(epoch * num_steps + idx)

When trying to load the checkpoint after SLL pretraining (1 epoch to test) with MoBY I get this error after using the `--pretrained` flag pointing to the checkpoint (I've tried...

Thanks for the solid and great work. Could you release the codes of swin transformer with performer attention. I have tried to reproduce the results of Tab. 6, but the...

please ask , swin transformer object detection , how to disable "instance segmentation feature"?

Thanks for your excellent work. I want to know if I enter 'python -m torch.distributed.launch --nproc_per_node 2 --master_port 12345 main.py', how can I single-step debugging?

Hi, i used evaluation classification code , but I get an error. Traceback (most recent call last): File "main.py", line 357, in main(config) File "main.py", line 89, in main model,...

In paper the digit is Swin-T 2242 29M 4.5G 755.2 81.3 FPS is 755.2 By running the code, apex o0: 680 apex o1: 949 apex o2: 1257 Could the authors...

How can I train my dataset with single gpu in window? I want to run my dataset with single gpu in windows for classification task.But I do not know how...

[Here](https://github.com/microsoft/Swin-Transformer/blob/main/models/swin_transformer.py#L208) you use 3 slices to generate mask, which generates 9 different kinds of masks. But if I understand it correctly, only 4 different kinds of masks (as you shown...