liusifei / uvc Goto Github PK
View Code? Open in Web Editor NEWJoint-task Self-supervised Learning for Temporal Correspondence (NeurIPS 2019)
License: MIT License
Joint-task Self-supervised Learning for Temporal Correspondence (NeurIPS 2019)
License: MIT License
Thanks for your excellent work. I have tried to run the test code (python test_with_track.py -s 480), and find an error:
Traceback (most recent call last):
File "test_with_track.py", line 21, in
from libs.vis_utils import norm_mask
ImportError: cannot import name 'norm_mask'
could you fix the test code? Thanks :-)
In model.py, line 187: self.grid_flat_crop = create_flat_grid(Fp_tar.size()).permute(0,2,1).detach()
I can't find the declaration of the variable 'Fp_tar', I wonder what the variable refers to?
Thanks a lot !
Good work. I have tried to run the training code, and find an error:
from model import track_match_comb as Model
File "/raid/codes/UVC/model.py", line 4, in
from libs.net_utils import NLM, NLM_dot, NLM_woSoft
ModuleNotFoundError: No module named 'libs.net_utils
So, can you upload the missing net_utils.py. Thank you very much.
Hi, thank you for providing your project. In this code, I can't find concentration regularization with a truncated loss in region tracking process mentioned in paper (Section:Moving as a unit.Eq.(6)). Could you please tell me where it is? Or if you did'nt upload the part of concentration regularization with a truncated loss, could you please upload this part?
Hi, thank you for sharing your great job. May I ask you if you could provide me with the Metrics implementation?
Thanks for releasing this great work!
Can I get the AP^{r}_{vol} score for the VIP dataset using "eval_vip.py"? It seems that only the mIoU score is computed in this file. Do I miss something? Thanks for your help.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.