David Chiu

Merge the pyi files into py files of optimizer

2

Merge the interfaces in pyi files into py files in `torch/optim`.

refactor: extract `get_lr` warning

1

Extract the `_get_lr_called_within_step` checking in the `get_lr()` of every LRSchedulers.

Merge the pyi files into py files of optimizer

2

Continue the work of pytorch/pytorch#125153

Fix: wrong ASGD implementation

6

> previous: Originally, the variables `new_eta` and `new_mu` would be constructed `len(grouped_mus)` times, but each of their values is the same and won't be changed. Therefore, it can be simplified...

Fix the redundant installation instructions.

1

The instructions are redundant with https://github.com/pytorch/audio/blob/7f6209b44a1b838e9f33fdd382a3c4ae14e8297f/docs/source/installation.rst?plain=1#L44-L48

Hello, In section 5 (Experiments) of your paper, it only states that you trained the model for 1 epoch using 1,000 images. However, the [training script](https://github.com/kwonminki/Asyrp_official/blob/main/script_train.sh) uses 100 images, which...