Comments (2)
Sorry that Matterport is a pain -- we would have released the images but weren't allowed to If the check is failing it means the images being generated on the fly are not the ones we used, so the numbers you get when you comment out the line are not comparable (and this is what I would expect -- hence having the check).
You have two choices:
-
You could just use the new set of images (but then please run an evaluation on KITTI or the RealEstate dataset to ensure that your version of pytorch is running the models correctly)
-
Try to diagnose why you're getting different generated images. My hunch is that it's because you're not loading in the dataset splits correctly. These splits are https://github.com/facebookresearch/synsin/tree/master/data/scene_episodes and they decide the environment to load in. These splits are generated if they are not found here, so the code would still run but the splits would be wrong. I would check that the right splits are being found in that part of the code. I hope that helps!
from synsin.
I also encountered this error, and I figured out that this was a habitat version issue.
After switching back to commits
habitat-sim: d383c2011bf1baab2ce7b3cd40aea573ad2ddf71
habitat-api: e94e6f3953fcfba4c29ee30f65baa52d6cea716e
as mentioned in #2 (comment), now the evaluation runs as expected.
from synsin.
Related Issues (20)
- How to produce the continuously changing video. HOT 1
- module 'pytorch3d.renderer.compositing' has no attribute 'CompositeParams' HOT 5
- Functionality of learn_feature HOT 2
- Neural point cloud renderer HOT 2
- Training on new dataset of rectangular images (H!=W) HOT 4
- Trying to train SynSin on SceneNet database HOT 11
- Discrepancy in sequence of operations inside ResNet block HOT 1
- Inference result does not match with the reported result HOT 3
- Would you recommend me a way to get 360 degree view? HOT 1
- No Downloading Permission of a video HOT 1
- calculation of the relative pose when processing kitti dataset HOT 1
- MIssing project files HOT 1
- Evaluation with a scale factor on RealEstate10K HOT 1
- Some issues to clarify HOT 4
- Is the attribution "lr" controlling learning rate?
- Try to use the code of Appearance Flow in synsin HOT 1
- Wrong setting with depth in PtsManipulator
- Scene episode generation about Matterport3D HOT 13
- habitat-sim install problem
- Inference time
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 synsin.