TODOs as of 11/29 - Githubissues

ZhaofengWu commented 5 years ago

[x] Seeding (Zhaofeng)
[x] Datasets should probably share char2idx as we want unseen chars to be generated as well (Joseph)
[x] Sort through the data points in increaseing video length
[x] Fix any dataset problem (e.g. micro not loading) (Joseph)
[ ] Check [INAUDIBLE] token #13 (Joseph)
[ ] Write something that puts dataloader/model/training/eval/logging/etc. together. Somethine like the current test_better_model.py but more sophisticated? Perhaps with tensorboard support (Joseph)
[x] Finish eval function with loss and CER output (Zhaofeng)
[ ] (optional) Plug in a WER implementation into eval function (Yutong)
- Maybe just write one ourselves
[x] Joint CTC+attention model (Zhaofeng)
[ ] CNN frame processing (Joseph)
[ ] Experiments. See #18. (Yutong & Joseph)
[ ] Inference (beam search) (Yutong)
[ ] Implement exact-foward-approximate-backward?

joseph-zhong commented 5 years ago

Fuck me.....

vdalv commented 5 years ago

^🙂 Something to do with this?

This looks like an interesting project. Best of luck, guys.

joseph-zhong / LipReading