Comments (12)
hi ! indeed this is not right. can you include your training and testing loss plots ?
from atlasnet.
Here is the visdom visualization
from atlasnet.
I just saw the issue about the pytorch version. Maybe that is my problem. I am using 0.3.1 version. I will try 0.4.0 and get back to you. Thanks.
from atlasnet.
I am actually using python 3.6. Judging by the table you provided, the Chamfer loss doesn't work with 3.6 and pytorch 0.4, is that correct?
from atlasnet.
definitly the pytorch version. your curves should look as in the readme. good luck !
from atlasnet.
apparently not (i don'r remember it exactly). it boils down to the chamfer distance code which is not compatible to every pytorch version. why not install a conda env with python 2.7?
from atlasnet.
I tried conda python 2.7 and pytorch 1.12 and training was stable. Thanks!
from atlasnet.
@ThibaultGROUEIX It seems that removing the batch normalization layers solves the instability issues during training due to pytorch versions. I was able to train the model without BN in python 3.6, pytorch 0.3.1 and achieve 1.81 loss for the autoencoder after 200 epochs.
from atlasnet.
unfortunatly, i can't provide support if you change the architecture but thanks for linking Chamfer error to batch norm!
regards, Thibault
from atlasnet.
actually i am not clear on if 1.81 is an issue or a success in your case. what error are you reporting ?
from atlasnet.
It’s not an error. I’m just pointing out a potential workaround for those who may want to use the architecture without reverting back to an old pytorch version.
from atlasnet.
Great ! Thanks for clarifying !
from atlasnet.
Related Issues (20)
- (Meshlab Visualization Trick ) Parts of faces flipped in the generated obj by train.py --demo HOT 1
- V2.2 dataset links are invalid (not the ones from V1) HOT 2
- some data download questions HOT 8
- Strangley poor results on pre-trained model HOT 6
- the pretrained resenet model under shapenet HOT 2
- Question about data HOT 2
- AtlasNet checkpoint not available HOT 5
- Question about train and test strategy HOT 2
- pymesh library HOT 1
- Compile Metro Distance (GPL3 Licence) HOT 1
- Question About Visulization HOT 2
- Weird results using pre-trained model HOT 1
- Question about running HOT 2
- Unable to find normalised mesh dataset in AtlasNetv2 HOT 3
- Mesh Parametrization Checkerboard Visualization HOT 4
- test HOT 3
- Learning representations for pointcloud manifold
- Cannot Load autoencoder_25_squares & Poor Performance on Pre-trained Model HOT 1
- AttributeError: module 'torch._C' has no attribute '_cuda_setDevice' HOT 4
- Error for final report generation.
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 atlasnet.