 xaviviro
|
fe947b6768
|
Merge pull request #59 from xaviviro/revert-55-test-torch
Revert "a hack to for onnxruntime to use cuda"
|
2023-06-27 20:39:38 +02:00 |
|
|
xaviviro
|
e7907c45b6
|
Revert "a hack to for onnxruntime to use cuda"
|
2023-06-27 20:39:24 +02:00 |
|
|
xaviviro
|
747726fc02
|
Merge pull request #56 from davidrobles/fix-broken-ffmpeg-link
Fix broken ffmpeg link
|
2023-06-27 14:26:47 +02:00 |
|
|
xaviviro
|
becb8a83bb
|
Merge pull request #55 from phineas-pta/test-torch
a hack to for onnxruntime to use cuda
|
2023-06-27 14:25:51 +02:00 |
|
|
David Robles
|
95ab7955c7
|
Fix broken ffmpeg link
|
2023-06-26 08:47:15 -07:00 |
|
|
Phan Tuấn Anh
|
4d3bdf8ee1
|
comments to understand why torch
|
2023-06-26 14:28:38 +02:00 |
|
|
Phan Tuấn Anh
|
91144be667
|
import torch
|
2023-06-26 14:19:44 +02:00 |
|
|
xaviviro
|
789cf77081
|
Merge pull request #47 from bandi13/standaloneScript
Add standalone script to get around filesize limitation
|
2023-06-21 10:52:10 +02:00 |
|
|
xaviviro
|
67c69136a5
|
Merge pull request #46 from bandi13/returnWhenFaceFound
Return when face found
|
2023-06-21 10:51:43 +02:00 |
|
|
Andras Fekete
|
dd65ab3a4a
|
Add standalone script to get around filesize limitation
|
2023-06-19 16:15:25 -04:00 |
|
|
Andras Fekete
|
19d039d145
|
Split out first_face vs multi-face calls
|
2023-06-19 13:21:11 -04:00 |
|
|
Andras Fekete
|
8e9035f712
|
5% Speed up
|
2023-06-19 10:50:58 -04:00 |
|
|
Andras Fekete
|
1388fc651f
|
Remove already swapped face from list
This gives a speedup on my machine, but will have the side effect of preferring faces earlier in the list
|
2023-06-19 10:27:45 -04:00 |
|
|
Andras Fekete
|
f6c006920d
|
Merge remote-tracking branch 'origin/main' into main
|
2023-06-19 09:58:55 -04:00 |
|
|
xaviviro
|
212e9fc532
|
Merge pull request #39 from bandi13/fix_memory
Process only 1k frames at a time to minimize memory footprint
|
2023-06-17 07:31:28 +02:00 |
|
|
xaviviro
|
208f7f3fdc
|
Merge pull request #40 from bandi13/add_docker
Add Dockerfile.nvidia
|
2023-06-17 07:30:50 +02:00 |
|
|
Andras Fekete
|
d5b88bad94
|
Merge branch 'add_docker' into main
|
2023-06-16 09:53:29 -04:00 |
|
|
Andras Fekete
|
0b64095e46
|
Better to use the hosts' version of refacer
|
2023-06-16 09:53:22 -04:00 |
|
|
Andras Fekete
|
fdae43c0a1
|
Add in inswrapper_128.onnx
|
2023-06-16 09:44:12 -04:00 |
|
|
Andras Fekete
|
1ba8369b98
|
Merge branch 'fix_memory' into main
|
2023-06-16 09:31:06 -04:00 |
|
|
Andras Fekete
|
eb7f75c470
|
Merge branch 'add_docker' into main
|
2023-06-16 09:31:02 -04:00 |
|
|
Andras Fekete
|
fabee094d0
|
Save outputs on the host
|
2023-06-16 09:17:34 -04:00 |
|
|
Andras Fekete
|
47cc73313b
|
Add Dockerfile.nvidia
|
2023-06-16 09:14:14 -04:00 |
|
|
Andras Fekete
|
a439a59296
|
Process only 1k frames at a time to minimize memory footprint
|
2023-06-16 09:04:25 -04:00 |
|
|
xaviviro
|
8f42e11e43
|
Merge pull request #33 from 24601/patch-1
fix(deps): address typo for COREML requirements
|
2023-06-11 05:29:16 +02:00 |
|
|
Basit Mustafa
|
35b17a529d
|
fix(deps): address typo for COREML requirements
|
2023-06-10 15:01:09 -06:00 |
|
|
xaviviro
|
61decb67a6
|
Merge pull request #26 from alunit3/main
Added type annotation to prevent parsing errors and makes the ngrok use ports from the server_port argument
|
2023-06-08 15:16:17 +02:00 |
|
|
Alunite
|
92f1b28e8d
|
Merge branch 'xaviviro:main' into main
|
2023-06-08 20:24:27 +08:00 |
|
|
Alunite
|
3e13367f85
|
Added types to arg and follows the server port from arg
Added types to the argument to prevent errors when parsing.
also makes the ngrok use ports from the server_port argument
|
2023-06-08 20:23:43 +08:00 |
|
|
xaviviro
|
a51089ea84
|
Update Refacer_colab.ipynb
|
2023-06-08 12:14:32 +02:00 |
|
|
xaviviro
|
0613ce21e6
|
Update README.md
|
2023-06-08 09:32:18 +02:00 |
|
|
xaviviro
|
dcba71aa60
|
Merge pull request #23 from fAIseh00d/main
Added gradio server IP and port
|
2023-06-08 09:24:34 +02:00 |
|
|
fAIseh00d
|
0e79a8a570
|
Added gradio server IP and port
|
2023-06-08 11:12:21 +04:00 |
|
|
xaviviro
|
82528d5b29
|
Merge pull request #21 from alunit3/main
Added ngrok support
|
2023-06-08 07:15:32 +02:00 |
|
|
Alunite
|
83b575d133
|
Forgot module import
|
2023-06-08 12:31:53 +08:00 |
|
|
Alunite
|
692adde98e
|
Added ngrok support
|
2023-06-08 12:28:14 +08:00 |
|
|
Xavi Vinaixa
|
63d501c34b
|
remove testsrc.mp4
|
2023-06-07 17:37:05 +02:00 |
|
|
Xavi Vinaixa
|
ff4b7f53e7
|
remove testsrc.mp4
|
2023-06-07 17:33:33 +02:00 |
|
|
Xavi Vinaixa
|
5bc01cf583
|
Fixed bug with hw accel ffmpeg encoders by testing them beforehand #12. Added command arg —colab_performance to maximize performance in Google Colab. Colab notebook updated.
|
2023-06-07 17:22:27 +02:00 |
|
|
Xavi Vinaixa
|
ef9b64ad92
|
Fixed bug for videos without audio, reactivated HW acceleration for ffmpeg
|
2023-06-06 12:54:22 +02:00 |
|
|
Xavi Vinaixa
|
f2e4dd93f4
|
Disabled TensorrtExecutionProvider due to a bug, it will now run with CUDAExecutionProvider on NVIDIA until we resolve error #9 #10
|
2023-06-06 12:39:20 +02:00 |
|
|
Xavi Vinaixa
|
4e833ec3d1
|
Disabled HW accel for FFMPEG need impromevents
|
2023-06-06 12:36:47 +02:00 |
|
|
Xavi Vinaixa
|
d9884e41fe
|
Disabled TensorrtExecutionProvider due to a bug, it will now run with CUDAExecutionProvider on NVIDIA until we resolve error #9 #10
|
2023-06-06 12:26:11 +02:00 |
|
|
Xavi Vinaixa
|
bbc10893b4
|
Commit message: Added support for hardware accelerators in ffmpeg. #5
|
2023-06-06 11:27:53 +02:00 |
|
|
Xavi Vinaixa
|
f5606ca4c4
|
Multithreading with TensorrtExecutionProvider #5.
|
2023-06-06 09:56:34 +02:00 |
|
|
Xavi Vinaixa
|
8008e2e766
|
TensorrtExecutionProvider
|
2023-06-06 08:14:28 +02:00 |
|
|
Xavi Vinaixa
|
a8d2941293
|
Incredible speed boost with TensorrtExecutionProvider #5.
|
2023-06-06 08:10:51 +02:00 |
|
|
Xavi Vinaixa
|
4a24df4755
|
Incredible speed boost with TensorrtExecutionProvider #5.
|
2023-06-06 08:05:58 +02:00 |
|
|
Xavi Vinaixa
|
7e628a3b83
|
Incredible speed boost with TensorrtExecutionProvider #5.
|
2023-06-06 08:04:33 +02:00 |
|
|
Xavi Vinaixa
|
b30d324e51
|
updated colab notebook with share_gradio
|
2023-06-06 07:56:23 +02:00 |
|