chenfeiyu fbc7e51fc9 1. add compute_statistics and normalize; ... 2. use jsonlines to read and write metadata by default; 3. use threadpool to replace processpool in preprocessing cause it is faster.		2021-06-18 02:49:49 +00:00
..
conf	WIP: add some trainig info	2021-06-14 17:21:45 +08:00
batch_fn.py	WIP: pwg training works	2021-06-14 17:05:37 +08:00
compute_statistics.py	1. add compute_statistics and normalize;	2021-06-18 02:49:49 +00:00
config.py	WIP: training setup done	2021-06-13 17:24:15 +08:00
normalize.py	1. add compute_statistics and normalize;	2021-06-18 02:49:49 +00:00
preprocess.py	1. add compute_statistics and normalize;	2021-06-18 02:49:49 +00:00
pwg_updater.py	move synchronize up before timer starts	2021-06-17 03:12:35 +00:00
train.py	use paddle's profiler	2021-06-16 13:43:13 +00:00