chenfeiyu
|
af26c1e389
|
fix priority in example/parallelwavegan
|
2021-06-30 13:33:56 +08:00 |
|
chenfeiyu
|
ef51e1ab13
|
refined training module
|
2021-06-30 13:08:23 +08:00 |
|
chenfeiyu
|
29b8b8b0ea
|
1. better error handling;
2. use absolute path in snapshot records;
3. visualdl takes a logger as init argument rather than creating one.
|
2021-06-27 18:53:45 +08:00 |
|
chenfeiyu
|
3e8a156348
|
add synthesis script for pwg
|
2021-06-26 19:31:52 +08:00 |
|
chenfeiyu
|
7e049a7744
|
add expanuser for preprocess, updater backward testing for pwg
|
2021-06-25 01:01:30 +08:00 |
|
chenfeiyu
|
542bbf6a81
|
add profiling tool and a config for parallel training
|
2021-06-24 14:53:38 +00:00 |
|
chenfeiyu
|
83c9f0aeae
|
add snapshot and visualizer
|
2021-06-21 09:56:26 +00:00 |
|
chenfeiyu
|
a738954001
|
1. change default data layout to channel last in preprocessing;
2. add Summary and DictSummary for aggrelation of evaluation losses;
3. add unittest for report ans scope.
|
2021-06-18 09:44:32 +00:00 |
|
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 |
|
chenfeiyu
|
30045cf602
|
move synchronize up before timer starts
|
2021-06-17 03:12:35 +00:00 |
|
chenfeiyu
|
58a988c789
|
add code to compute statistics
|
2021-06-16 16:18:13 +00:00 |
|
chenfeiyu
|
042e02d242
|
use paddle's profiler
|
2021-06-16 13:43:13 +00:00 |
|
chenfeiyu
|
8dbcc9bccb
|
add profiling
|
2021-06-16 09:40:47 +00:00 |
|
chenfeiyu
|
bbbe5a8b50
|
add profiling
|
2021-06-16 14:47:30 +08:00 |
|
chenfeiyu
|
95f64c4f02
|
WIP: add some trainig info
|
2021-06-14 17:21:45 +08:00 |
|
chenfeiyu
|
b0983e4d76
|
WIP: pwg training works
|
2021-06-14 17:05:37 +08:00 |
|
chenfeiyu
|
54c7905f40
|
WIP: training setup done
|
2021-06-13 17:24:15 +08:00 |