Comments (2)
Hi @hbishop1:
- I empirically found EMA to accelerate training (eval performance increases faster) and improve performance (by <5%), but the policy should "work" even without it.
- I found the causal attention masking to be critical to get the transformer variant of diffusion policy to work. My suspicion is that when used without it, the model "cheats" by looking ahead into future end-effector poses, which is almost identical to the action of the current timestep.
- I think the model capacity needed depends on task complexity (more complex task requires larger CNN). Reducing the number of training diffusion steps also reduces CNN capacity requirement at the expense of reduced action quality. ~10M CNN should still work with less than 10% performance penalty on benchmarks we have tested.
from diffusion_policy.
Great, thanks for the quick and detailed response, that will really help!
from diffusion_policy.
Related Issues (20)
- about eval results of pushT, is this normal?
- Failure to eval with other checkpoints HOT 1
- About collecting data in real robot scene
- Metadata info about the dataset?
- Segmentation fault probably associated with OpenGL or multithreading? HOT 1
- Can you help explain what are the two dimension of parameter 'robot0_gripper_qpos' stand for?
- how to visualize the trajectory
- code for teleoperation using Quest? HOT 1
- Training loss is relatively large
- Why we must to use MultiStepWrapper? HOT 2
- Question on pusht real data? HOT 1
- how to use multiGPU HOT 1
- why when evaluating a pretrained checkpoint, the test/mean_score in eval_log.json is not equal to the test_mean_score in the checkpoint
- Maybe ther is a bug in the code of diffusion_policy.model.diffusion.conditional_unet1d.py line 143:
- Unable to Access Project Webpage and Training Data HOT 2
- Why does that model need the environment?
- dataset format
- Is it possible to release the code for the mid-level controller used in Franka? HOT 1
- chat group
- DOES DP REALLY WORK ON REAL TASK?
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 diffusion_policy.