search

microsoft / Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
https://arxiv.org/abs/2103.14030
MIT License
13.82k stars 2.05k forks source link

swin transformer does not support dynamic input shape after tracing model #301

Open fatemebafghi opened 1 year ago

fatemebafghi commented 1 year ago

hello there, I am trying to convert swin model to onnx and then tensorrt, but a problem which I face is that it does not support dynamic input resolution after tracing the model using torch.jit.trace. It seems that it is because of the mask input in window attention. Do you have any idea how I can fix this problem?

jeiva2000 commented 1 year ago

I have the same problem

canyagmur commented 1 year ago

I also need dynamic input shape feature.

yyyyyxie commented 4 months ago

I also need the feature of dynamic input shape. I've spent a long time but haven't solved this issue yet.