Commit Graph

167 Commits

Author SHA1 Message Date
Somdev Sangwan
7cbffe4a6f
Update requirements.txt 2023-05-31 14:37:59 +05:30
Somdev Sangwan
4867f356ef
fix gpu issues for some envs 2023-05-31 12:43:43 +05:30
Somdev Sangwan
1cc34ce8e0 bruh moment 12 2023-05-31 12:42:34 +05:30
Somdev Sangwan
077b931cef
Rename globals.py to core.globals.py 2023-05-31 12:41:41 +05:30
Somdev Sangwan
278735d6a6
Merge pull request #157 from SaqibAMA/main
Fix: Added missing `rreplace` import from core.utils.
2023-05-31 11:40:55 +05:30
Saqib Ali
ccd63b1dce
Fix: Added missing rreplace import from core.utils.
An import for `rreplace` was missing from core.utils in the run.py file which made the program crash. It has been fixed and added.
2023-05-31 10:53:13 +05:00
Somdev Sangwan
7e68260f71
bruh moment 11 2023-05-31 10:38:16 +05:30
Somdev Sangwan
6a09ee0c4b
handle non-nvidia gpus better 2023-05-31 10:36:18 +05:30
Somdev Sangwan
1aacdb0d62
onnxruntime-gpu -> onnxruntime 2023-05-31 10:27:18 +05:30
Somdev Sangwan
450f8fade7
clarity 2023-05-31 10:16:56 +05:30
Somdev Sangwan
6416d4ebe8
Merge pull request #155 from ShivamKumar2002/patch-1
Fix GPU not being used even when it available
2023-05-31 09:39:14 +05:30
Somdev Sangwan
c2ce47dec5
Merge pull request #151 from Moeblack/TensorRTExcutionProvider-error
fix TensorRTExcutionProvider errors
2023-05-31 09:37:44 +05:30
Shivam Kumar
9c1ea4fa01
Fix GPU not being used even when it available
On lots of systems onnxruntime doesn't detect GPU unless pytorch is imported before it. So despite having CUDA and CUDNN setup correctly, it is only using CPUExecutionProvider. By importing pytorch first, the issue is fixed. So let's use this until any official solution is available.

See: https://stackoverflow.com/questions/75294639/onnxruntime-inference-with-cudnn-on-gpu-only-working-if-pytorch-imported-first
2023-05-31 09:20:41 +05:30
Pikachu~~~
4183e71cf8
fix TensorRTExcutionProvider errors 2023-05-31 10:06:42 +08:00
Henry Ruhs
6258f3c084
Update processor.py 2023-05-31 02:44:58 +02:00
Somdev Sangwan
251fde9596
Merge pull request #91 from henryruhs/main
Introduce pre_check() and limit_resources()
2023-05-31 02:27:34 +05:30
henryruhs
411818d0f9 Need to return at least 2 cores for default 2023-05-30 22:44:48 +02:00
henryruhs
3e35bea1df Adjust max-cores with lower default 2023-05-30 22:16:38 +02:00
henryruhs
5feb6b0d71 Resolve absolute model path 2023-05-30 21:52:39 +02:00
henryruhs
98a5111d53 Undo: Resolve absolute model path 2023-05-30 21:48:06 +02:00
Henry Ruhs
f50337f708
Merge branch 'main' into main 2023-05-30 21:13:15 +02:00
henryruhs
ffc2bd2485 Resolve absolute model path 2023-05-30 21:12:19 +02:00
Henry Ruhs
4911143338
Merge pull request #138 from Symbiomatrix/clean1
Cleanup of core count.
2023-05-30 20:53:57 +02:00
Symbiomatrix
c3c44b62dd
Update run.py 2023-05-30 21:47:41 +03:00
henryruhs
47dafb48ba Normalize cli args 2023-05-30 20:43:03 +02:00
henryruhs
864e2fe9db Normalize cli args 2023-05-30 20:42:54 +02:00
Henry Ruhs
cfa9c6cfe9
Merge branch 'main' into main 2023-05-30 20:38:46 +02:00
Somdev Sangwan
0adf2a7091
fix cases where CUDA_VERSION is None 2023-05-30 22:58:39 +05:30
RealCalumPlays
e4f1d9aaff
Update README.md to include --cores parameter (#128)
* Update utils.py

* Update README.md
2023-05-30 22:05:36 +05:30
Somdev Sangwan
de7d384bca
Merge pull request #127 from Symbiomatrix/files2
Fix for filename selection.
2023-05-30 22:05:06 +05:30
Somdev Sangwan
cb2ff52678
just use Path 2023-05-30 22:04:38 +05:30
Symbiomatrix
a3617b1cff
Update run.py 2023-05-30 19:29:33 +03:00
Somdev Sangwan
afefc37856
Merge pull request #124 from FurkanGozukara/main
Improves final output video quality significantly
2023-05-30 21:45:31 +05:30
Furkan Gözükara
561397ab05
Improves final output video quality significantly
Improves final output video quality significantly
2023-05-30 19:07:20 +03:00
Somdev Sangwan
339e531a2e --cores option 2023-05-30 20:30:43 +05:30
henryruhs
80fe3721ee Remove debug output 2023-05-30 16:36:03 +02:00
Henry Ruhs
c10e37cd2f
Merge branch 'main' into main 2023-05-30 16:33:02 +02:00
henryruhs
41c69d318d Create face analyser and face swapper instance on demand 2023-05-30 16:29:58 +02:00
Somdev Sangwan
f0aad74e0d
update pillow version 2023-05-30 19:19:11 +05:30
Somdev Sangwan
90e2ba0fc7 properly name output file when its an image 2023-05-30 19:07:22 +05:30
Henry Ruhs
0d2fbca4ce
Merge branch 'main' into main 2023-05-30 15:32:07 +02:00
Somdev Sangwan
03ac74edac fix status bar 2023-05-30 18:54:08 +05:30
henryruhs
36e3391ca2 Asking for Python 3.8+ 2023-05-30 15:21:37 +02:00
henryruhs
1113e4cc83 Use ctypes to allocate memory in Windows 2023-05-30 15:19:47 +02:00
henryruhs
c8e1a99118 We need Python 3.4+ 2023-05-30 15:14:42 +02:00
henryruhs
ff7343c2fa We need Python 3.4+ 2023-05-30 15:14:18 +02:00
Somdev Sangwan
d1030654ce
add onnxruntime-gpu 2023-05-30 18:39:17 +05:30
Somdev Sangwan
d3c86fb34b
Update issue templates 2023-05-30 18:12:38 +05:30
Somdev Sangwan
bfa7ad8f65
add bug report template 2023-05-30 18:06:29 +05:30
Somdev Sangwan
28d449483b
Merge pull request #101 from xaviviro/audio-sync
Fix: Audio Synchronization Issue Resolved
2023-05-30 17:26:01 +05:30