search

Artanic30 / HOICLIP

CVPR 2023 Accepted Paper HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models
52 stars 7 forks source link

error of the CLIP image_encoder #2

Closed hangzhiyiwei closed 1 year ago

hangzhiyiwei commented 1 year ago

Hi, thank you for your nice work.

I came across an error here https://github.com/Artanic30/HOICLIP/blob/main/models/models_hoiclip/gen.py#L121.

''' Exception has occurred: ValueError too many values to unpack (expected 2) '''

I referred to the CLIP description, and the output of "encode_image" method is only one. https://github.com/openai/CLIP/blob/main/clip/model.py#L340. Maybe there is something missing in your code?

Any reply will be appreciated. Thank you very much.

Artanic30 commented 1 year ago

Sorry, I forgot to upload modifed CLIP codes. The issue is fixed in https://github.com/Artanic30/HOICLIP/commit/eca6c460e3758c8ee56e73f716cad78fb565c2d9 Thanks for pointing out the bug.