czczup / ViT-Adapter

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
https://arxiv.org/abs/2205.08534
Apache License 2.0
1.23k stars 137 forks source link

how to deploy using TensorRT? #180

Open chenzhutian opened 2 months ago

chenzhutian commented 2 months ago

Thanks for the repo.

I try to follow the instruction in https://github.com/OpenGVLab/InternImage/tree/master/segmentation to deploy ViT-Adapter into TensorRT but failed with error "RuntimeError: Dangling node reference"

Do you have any pointers and hints to solve this?

Thank you!

22ema commented 1 month ago

@chenzhutian Could you solve this problem?