 nagadomi
|
89c8f5db8e
Add aux_lbp; Fix oracle
|
%!s(int64=6) %!d(string=hai) anos |
|
nagadomi
|
29260ede24
fix batchwise psnr
|
%!s(int64=8) %!d(string=hai) anos |
|
nagadomi
|
451ee1407f
Stop calculate the instance loss when oracle_rate=0
|
%!s(int64=8) %!d(string=hai) anos |
|
nagadomi
|
c89fd7249a
Add learning_rate_decay
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
70a2849e39
Fix missing file
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
68a6d4cef5
Use MSE instead of PSNR
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
a938cd5994
Reduce draw calls
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
1900ac7500
Use PSNR for evaluation
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
aaac6ed6e5
Refactor training loop
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
b35a9ae7d7
tuning
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
490eb33a6b
Minimize the weighted huber loss instead of the weighted mean square error
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
8dea362bed
sync from internal repo
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
2231423056
update training script
|
%!s(int64=10) %!d(string=hai) anos |
