rendezvous icon indicating copy to clipboard operation
rendezvous copied to clipboard

A transformer-inspired neural network for surgical action triplet recognition from laparoscopic videos.

Results 4 rendezvous issues
Sort by recently updated
recently updated
newest added

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...

When I reproduced the code for the RDV article(RDV split), my result remains about 0.6784 | 0.4404 | 0.2609 | 0.1923 | 0.1316 | 0.0994 ,which are largely different from...

The link to low res weights for the pytorch Cholect45 (crossval k1) seems to not match the model (https://s3.unistra.fr/camma_public/github/rendezvous/rendezvous_l8_cholect45_crossval_k1_layernorm_lowres.pth): size mismatch for decoder.mhma.0.ln.weight: copying a param with shape torch.Size([100, 8,...

The link to low res weights for the pytorch Cholect50 (RDV) seems to direct to the same/root page: "https://github.com/CAMMA-public/rendezvous/blob/main".