search

CAMMA-public / rendezvous

A transformer-inspired neural network for surgical action triplet recognition from laparoscopic videos.
Other
24 stars 8 forks source link

Question about the pretrained module #23

Closed bot-white-g1ve closed 2 months ago

bot-white-g1ve commented 7 months ago

Hi, thanks for your great job.

But I've found an issue with the pretrained module's weight. In the essay, you have mentioned that 35 videos are used for training, 5 videos for validation and 10 for testing. However, when I use your pretrained weight to test 5 val videos, the accuracy reaches 90% which may be weird if these 5 videos haven't been used for training.

Are these released pretrained weights also generated from training on these 5 val videos?

nwoyecid commented 2 months ago

Dear user,

Please acquaint yourself with the dataset splits in https://arxiv.org/pdf/2204.05235 for the correct use of the dataset split and model weights.

Thanks