Comments (8)
I'm not sure we can release that model due to copyright issue.
The training code is committed now, so you're welcome to try it yourself.
from vid2vid.
@tcwang0509 It would be great if the model could be released (or maybe a new model with training data that can be used).
As most people won't have a DGX1 available, training the 2K resolution net for 10 days on a p3.16xlarge instance (also has 8 V100 GPUs) would cost USD 5875 on AWS. (USD24.48 per hour on-demand pricing * 24 hours/day * 10 days)
And it seems that this won't even work as you state at least 24GB memory is required per GPU. I am not even aware of any cloud provider currently offering GPUs with more than 16GB.
from vid2vid.
@petergerten the requirements you mentioned is for training Cityscapes. For pose even on single GPU it should just take 5-7 days.
from vid2vid.
@tcwang0509 great, thanks for the clarification
from vid2vid.
The research is very exciting!
I also hope the pretrained model will be released~
from vid2vid.
@tcwang0509 For face how many days will it take?
from vid2vid.
So I've found a pre-trained model used by densepose.
https://dl.fbaipublicfiles.com/densepose/DensePose_ResNet101_FPN_s1x-e2e.pkl
Now, if only there was a way to convert this densepose model to a format used by vid2vid. Assuming both libraries use the same formatting to declare the input & output tensors, would this be possible?
I'm new to pytorch so please pardon the noob question.
from vid2vid.
So I've found a pre-trained model used by densepose.
https://dl.fbaipublicfiles.com/densepose/DensePose_ResNet101_FPN_s1x-e2e.pklNow, if only there was a way to convert this densepose model to a format used by vid2vid. Assuming both libraries use the same formatting to declare the input & output tensors, would this be possible?
I'm new to pytorch so please pardon the noob question.
Any update on this one. This seems a good approach to get the pretrained model for pose?
from vid2vid.
Related Issues (20)
- test only with keypoints
- [QUESTION] Google colab HOT 1
- Where is the "pre-trained segmentation algorithm" in the repo?
- Sequence length: How to limit that to 30, it is increasing automatically as the no. of epochs is increasing
- Using Openpose docker image with vid2vid
- Is there any ways to improve the output quality of the pose model?
- Sometimes ran into RuntimeError: Given groups=1, weight of size [64, 18, 7, 7]... when training. HOT 3
- Inference time - How much FPS is possible?
- Error HOT 1
- How to test “pose-to-body”?
- RuntimeError: CUDA error: throwing an instance of 'c10::Error' HOT 1
- Vid HOT 1
- RuntimeError: Legacy autograd function with non-static forward method is deprecated. HOT 2
- FID evaluation
- Errors when running on CPU without CUDA
- RuntimeError: DataLoader worker (pid(s) 22100) exited unexpectedly HOT 1
- AttributeError: module 'torch._C' has no attribute '_cuda_setDevice' HOT 1
- "Pretrained network G0 has fewer layers..."
- Nivda
- Download gdrive doesn't work - need to manually download model for now 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 vid2vid.