anosorae / IRRA

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval (CVPR 2023)
MIT License
205 stars 27 forks source link

A small bug #2

Closed YwSama closed 1 year ago

YwSama commented 1 year ago

In model/build.py, line 136, there is no method named "compute_mcm_or_mlm".

anosorae commented 1 year ago

Thank you for pointing out this bug. You can fix it by changing it to 'compute_mlm'.