Jean-Marc Valin
|
efeaa8aef8
|
Make weights blob a void*
|
2024-03-02 17:36:09 -05:00 |
|
Jean-Marc Valin
|
6a9831a6b0
|
Remove run-time code for old TF2 models
No longer needed now that PLC is trained with PyTorch stack
|
2024-01-21 02:11:50 -05:00 |
|
Michael Klingbeil
|
12fbd8111a
|
use opus_(re)alloc and opus_free for dnn and DRED related functions
|
2023-12-15 15:48:58 -05:00 |
|
Jean-Marc Valin
|
1032e47d3f
|
more cleanup
|
2023-10-20 15:13:43 -04:00 |
|
Jean-Marc Valin
|
f0ec990dba
|
Switching to neural pitch estimator
Remove old pitch estimator and retrain all models
|
2023-10-06 03:14:56 -04:00 |
|
Jean-Marc Valin
|
b50ddccf0e
|
Fixes weights parsing with DISABLE_DEBUG_FLOAT
It's the name that's NULL when an array isn't found
|
2023-07-28 18:29:33 -04:00 |
|
Jean-Marc Valin
|
b075eb535a
|
oops, fix linear_init()
|
2023-07-27 19:54:10 -04:00 |
|
Jean-Marc Valin
|
8e7080903d
|
Make float_weights optional
|
2023-07-23 18:25:14 -04:00 |
|
Jean-Marc Valin
|
d15be43af4
|
Make bias/subias/diag/scale optional
|
2023-07-23 18:11:15 -04:00 |
|
Jean-Marc Valin
|
9d40e5cb08
|
Add loading for LinearLayer
Untested
|
2023-07-23 14:49:13 -04:00 |
|
Marcus Asteborg
|
f36685fc97
|
Remove trailing whitespace in dnn
|
2023-06-22 13:58:37 -07:00 |
|
Jean-Marc Valin
|
db48088e9f
|
Should fix some missing #include problems
|
2023-06-22 03:22:20 -04:00 |
|
Jean-Marc Valin
|
ec6e42ba3d
|
misc fixes
|
2023-05-31 15:58:11 -04:00 |
|
Jean-Marc Valin
|
d98c59fb9a
|
Add missing #include
|
2023-05-25 17:30:19 -04:00 |
|
Jean-Marc Valin
|
c7b6935bf2
|
Add validation for weights blob
|
2023-05-20 14:23:02 -04:00 |
|
Jean-Marc Valin
|
3cd7588dae
|
Avoid potential integer wrap-around
|
2023-05-18 00:04:11 -04:00 |
|
Jean-Marc Valin
|
580614f062
|
Make the code C90-compliant
|
2023-05-17 04:09:04 -04:00 |
|
Jean-Marc Valin
|
71c8a23fc1
|
Code for building a model struct
|
2023-05-16 23:15:49 -04:00 |
|
Jean-Marc Valin
|
cc714cc5b0
|
binary weights work in progress
|
2023-05-16 16:47:12 -04:00 |
|