Closed ycmin95 closed 1 year ago
Thanks for raising this issue.
We changed the prune_embedding.ipynb a bit when preparing the released code, increasing the number of glosses from 2004 to 2009.
For evaluating the downloaded model, please use the gloss_embeddings.bin provided here.
You need to retrain a model if you use the gloss_embeddings.bin generated by yourself. Try again and see if you can reproduce the results. Thanks.
Thanks for your quick reply, I successfully conducted the evaluation with the provided embedding.
Thanks for sharing the SLRT codebase, and I want evaluate the provided checkpoints in this repo.
I following the readme to setup the environment and download the checkpoints, and when I evaluate the checkpoints, it reports the weights size mismatch error, as shown below:![1690426239313](https://github.com/FangyunWei/SLRT/assets/23148691/83f2c807-b9d8-47bc-b428-41f23713a6f1)
Similar problem also appears in the two-stream setting:![1690426187866](https://github.com/FangyunWei/SLRT/assets/23148691/ba24dcbe-0007-47b1-9221-5ade45e0cb87)
I try to locate the origin of this error, based on the prune_embedding.ipynb, the final classifier should be torch.Size([6386, 1024]) and the gloss_embeddings should be 2009. However, the load weights are ([6308, 1024]) and 2004, is anything here I misunderstand?![1690426869666](https://github.com/FangyunWei/SLRT/assets/23148691/c723d67e-28d3-426f-949d-62d8119193f6)
Thanks for your time and looking for your reply~