Comments (2)
Hi,
Thanks for your kind words and interest in our work.
Q: When training on real robot data, did you start the training from scratch or was there any preliminary training involved using simulations?
A: We train on real robot data from scratch.
Q: During your experiments with real robot data, did you observe a similar convergence pattern between translation and rotation?
A: This is a great question! Yes, we observed a similar convergence pattern, so what you observe is typical. I would strongly recommend visualizing the predicted translation heatmap on top of virtual images of some train as well as unseen samples. My guess would be that you would observe sharp heatmap predictions. If it is so, it would suggest that the network has converged well and the seemingly (explained below) higher value of the translation loss is not an issue.
Unlike typical losses, which go to 0, the translation loss in RVT does not go to zero but hovers around 3.8 ( probably less for better-trained networks) for an image resolution ~220ish and some other parameters like gt_hm_sigmae. This is because, in RVT, translation loss is the sum of heatmap prediction loss for each virtual image. Predicting the ground-truth heatmap exactly requires predicting the keypoint location on the virtual image with sub-pixel accuracy. As the 3D ground-truth keypoint location can be mapped as a continuous 2D pixel location. This is just a design choice, we could have chosen to map to a discrete pixel location. Since, a network incurs a large loss value even for predicting the keypoint apart by <1 pixel distance, the loss values are large.
from rvt.
Many thanks for your reply! Indeed visualisation does show very reasonable results. Thank you so much!
from rvt.
Related Issues (20)
- Does the line 150 give a Cartesian coordinate of a pixel? HOT 6
- Why is time an essential part of low_dim_state? HOT 2
- Can I run eval.py with multiple processes? HOT 2
- Questions about inference speed HOT 2
- How to train and test with an image_size resolution of 256*256? HOT 4
- About models training HOT 2
- About model training in the real-world HOT 2
- add_final and repeat in replay HOT 4
- [Training] How to evaluate when training? HOT 2
- Questions about the details HOT 5
- About the tp1 in replay HOT 3
- Does the RVT model control Franka robot in Isaac-sim? HOT 4
- Data collection issues HOT 4
- question about camera calibration in real world HOT 8
- AttributeError: 'CustomMultiTaskRLBenchEnv2' object has no attribute 'get_ground_truth_action' HOT 1
- Rendered image with color noise in the background HOT 4
- Question about the up direction of "front" and "back" camera in renderer.py HOT 2
- Details about the real-world experiments HOT 4
- Questions about the scene bounds and img aug in real-robot experiments HOT 4
- Issues while running the training script
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 rvt.