Comments (8)
You can try reducing these these two parameters: --face_det_batch_size
and --LNet_batch_size
.
Or you can run the code in colab: https://colab.research.google.com/github/vinthony/video-retalking/blob/main/quick_demo.ipynb
from video-retalking.
But there is no --face_det_batch_size and --LNet_batch_size in the inference.py
from video-retalking.
You can try reducing these these two parameters:
--face_det_batch_size
and--LNet_batch_size
. Or you can run the code in colab: https://colab.research.google.com/github/vinthony/video-retalking/blob/main/quick_demo.ipynb
Excuse me, I have the same problem, cuda out of memory. Where are these two parameters? I'd like to reduce them. thx.
from video-retalking.
I met the same error,how resolve it ?
from video-retalking.
I met the same error,how resolve it ?
You can try smaller batch size:
python3 inference.py \
--face examples/face/1.mp4 \
--audio examples/audio/1.wav \
--outfile results/1_1.mp4 \
--face_det_batch_size 2 --LNet_batch_size 2
from video-retalking.
utils/inference_utils.py
here
from video-retalking.
I modified two values of batch_size. My video card is V100 with 32G of video memory, but it still bursts. Does the program need to be optimized?
from video-retalking.
it's ok to running on 8GB vram machine. you just need to adjust the input video parameter to reduce the consumption of vram to prevent the issue of "out of cuda memory". example for reduce Sampling Rate of video, remove the sound of input video, choose "CBR" for input video.
from video-retalking.
Related Issues (20)
- Is there ANYWAY, to make this FAST, FASTER? And to use GPU, Pytorch, Batchj size etc? HOT 6
- When will the training code for the model be made public? HOT 2
- UnboundLocalError: local variable 'mask_sharp' referenced before assignment HOT 3
- Accessing elements in a 2D array
- ModuleNotFoundError: No module named 'face_alignment'
- nvrtc compilation failed + 'keypoints' errors HOT 1
- Problem producing high resolution output HOT 9
- 您好,请问一下可以重新进行训练模型吗?我觉得对于中文语音来说,7秒之内唇形很准确,但是7秒之后就不准了,有些停顿的地方都不停顿。
- SSL Issue with usage HOT 1
- TensorBody.h:338:30: note: declared here 338 | DeprecatedTypeProperties & type() const
- sieve improvements HOT 4
- 提升生成速度
- model running speed
- [Step 5] FaceDet:: 0%|
- 请问传入什么样的mp4文件会获得较好的效果
- 求助,折腾48小时了,还没好,报错解决不掉 HOT 4
- UnboundLocalError: local variable 'keypoints' referenced before assignment HOT 3
- Lips don't sync on big faces. HOT 1
- ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor' HOT 9
- RuntimeError: PytorchStreamReader failed reading file data/36: file read failed HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from video-retalking.