Comments (4)
Hello Cheng,
Re: Preprocessed data. We can (now) share preprocessed data on a per-request basis with people who have signed the ShapeNet user agreement. The reason we don't distribute it publicly is that we are trying to respect the ShapeNet license.
Re: Pretrained models. I know having access to pretrained models is very important and it is currently the highest priority for the codebase. Currently I think it will be at least a few weeks before they are ready to push to the public repository. In the mean time, I could share a checkpointed model with you directly, though it does not fully reproduce the paper numbers (the original paper checkpoints were trained for ~3.5M steps with a datacenter pipeline and are incompatible with the open-source release, so I am retraining the models locally). In the long-term it would be good to add local multi-gpu support so that training time is less of an issue.
from ldif.
Thanks for your patience! I'll try to contact you personally to get a pretrained model.
from ldif.
Hello Cheng,
Re: Preprocessed data. We can (now) share preprocessed data on a per-request basis with people who have signed the ShapeNet user agreement. The reason we don't distribute it publicly is that we are trying to respect the ShapeNet license.
Re: Pretrained models. I know having access to pretrained models is very important and it is currently the highest priority for the codebase. Currently I think it will be at least a few weeks before they are ready to push to the public repository. In the mean time, I could share a checkpointed model with you directly, though it does not fully reproduce the paper numbers (the original paper checkpoints were trained for ~3.5M steps with a datacenter pipeline and are incompatible with the open-source release, so I am retraining the models locally). In the long-term it would be good to add local multi-gpu support so that training time is less of an issue.
Hi, really nice work! I wonder if I could get a pre-trained model as well. I'm working on 3D reconstruction tasks and want to compare with your work. Really appreciated!!
from ldif.
@chengzhag have you got the pre-trained model , I also want to get the pre-trained model as well , would you please to share it with me, ThankYou!
from ldif.
Related Issues (13)
- Fix issues while running ./build_gaps.sh HOT 3
- /process_mesh_local.sh: line 47: 13856 Bus error (core dumped) ${gaps}/msh2msh $mesh_in $mesh -scale_by_pca -translate_by_centroid -scale 0\.25 -debug_matrix ${outdir}/orig_to_gaps.txt
- Segmentation fault when train the net HOT 3
- Visualization with qview: scaling issue
- Abnormal chamfer metric reproduced on ShapeNet HOT 8
- no limitation for "%s" while calling fscanf()
- Error when unit testing
- The result of unit_test.sh HOT 1
- IO Performance Issues HOT 2
- Crash on train HOT 1
- test or val issue HOT 2
- Error in data preprocessing HOT 1
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 ldif.