adldotori / clothflow Goto Github PK
View Code? Open in Web Editor NEWClothFlow Implementation
ClothFlow Implementation
Hi Adldotori,
I am reading your paper "ClothFlow" and am very appreciate for your work.
Although this article is a few years age, it has laid a solid foundation in this field, so I am trying to reconstruct the training process of ClothFlow and encountered some problems at stage0, (data preparation I guess).
I have downloaded the MVC data and completed the size conversion with resize.py.
From your code, it seems that make_dataset.py and make_seg.py are used to complete the seg and pose steps, which will call CIPH_PGN and pytorch_Realtime_Multi-Person_Pose_Estimation to do the related work.
When using make_dataset.py and make_seg.py, I used sys.path.add to specify the relevant paths, but encountered errors: No module named 'a_pose' and No module named 'seg'.
I also noticed that you called the segmentation and pose functions, but I did not see these two functions in these two related projects you mentioned and your code also. If you have also modified the two codes you mentioned, could you please kindly put the relevant parts in this project together or release them in any way.
I am very grateful for your work and look forward to your reply. All the best.
what is theta_generator role in stage 2?
I think it is a pretrained model. after it, the processed input will feed in flownet model.
theta_generator = ClothNormalizer(nc=nc)
load_checkpoint(theta_generator, init_CN)
theta = theta_generator(con_cloth_mask, tar_cloth_mask)
grid1 = projection_grid(theta, con_cloth_mask.shape)
grid2 = projection_grid(theta, con_cloth.shape)
con_cloth_mask = Ft.grid_sample(con_cloth_mask, grid1).detach()
con_cloth = Ft.grid_sample(con_cloth, grid2, padding_mode="border").detach()
con_cloth = con_cloth * con_cloth_mask + (1 - con_cloth_mask)
[F, warp_cloth, warp_mask] = model(torch.cat([con_cloth, con_cloth_mask], 1), tar_cloth_mask)
How to install requirements.txt? I found that both pip and conda cannot install it successfully.
Thanks for your excellent work !
Are there any link to download trained model for testing image?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.