About using RN50 as image encoder

anosorae / IRRA

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval (CVPR 2023)

MIT License

183 stars 25 forks source link

Closed sunmenmian closed 1 year ago

sunmenmian commented 1 year ago

Hello, thanks for your good paper. And how can I run this code with resnet50 pre-trained weights?

anosorae commented 1 year ago

Comment out this line of code and uncomment the next line of code for this line. i.e. L84 and L97