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 authors, I tried to compute the cosine similarity of the pretrained swin-tiny output without average pooling. (7x7 patch each with 1000 dim) The visualization below shows the patches at...

Hi Swin Transformer team, We've recently added Swin Transformer to HuggingFace Transformers: https://huggingface.co/docs/transformers/master/en/model_doc/swin. All checkpoints are on the hub: https://huggingface.co/models?other=swin. The cool thing about the hub is that it's entirely...

Hi authors, Following the official training command below, I observed unstable training loss and accuracies around epoch # 20. `python -m torch.distributed.launch --nproc_per_node 8 --master_port 12345 main.py \ --cfg configs/swin_base_patch4_window7_224.yaml...

I am trying to use SWIN Transformers for a problem that maps every image to a score of 1 to 100 When in initialize the model, everything works fine. But...

Has anybody thought about implementing 1D Swin Transformer? It should also be interesting to apply Swin Transformer to time-series data analysis.

Hi, I am trying to visualize the self attention maps on my input image trying to extract them from the model, unfortunately I am not succeeding in this task. Could...

1 why do you construct the val sampler as a random sampler rather than a sequence sampler? It may be inconvenient when inferencing on test data. https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/data/build.py#L41 https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/data/samplers.py#L23 2 The...

Thanks for the great work! I find the Swin V2 on arxiv just now, looking forward to the code of v2!

When I use --zip to train the swin-T, raise error: torch.distributed.elastic.multiprocessing.errors.ChildFailedError Dataset: ILSVRC2012 OS: ubuntu20.04 pytorch: 1.10 RAM: 32G The program can work without --zip, but it is very slow.