search

Syliz517 / CLIP-ReID

Official implementation for "CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels" (AAAI 2023)
MIT License
285 stars 45 forks source link

About the reid model of the vehicle #32

Open 972821054 opened 8 months ago

972821054 commented 8 months ago

First of all, thank you very much for your contribution in the field of re-identification! I had some problems when using your model. When I read the vehicle model into it, some tensor size mismatch problems were displayed. When training vehicle data, what should you do for the ViT backbone? What modifications were made? image image

AtiChetsurakul commented 6 months ago

I think your config file is wrong. It should be like this: Resized position embedding: %s to %s torch.Size([197, 768]) torch.Size([257, 768])