search

Aaditya-Prasad / consistency-policy

[RSS 2024] Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation
https://consistency-policy.github.io/
MIT License
94 stars 7 forks source link

infer single rgb image #5

Closed PredyDaddy closed 1 month ago

PredyDaddy commented 1 month ago

Hello, thank you for your excellent work. I would like to ask, if I only have an RGB image, how can I generate the corresponding grasping path? Which script in the repository should I use?

Aaditya-Prasad commented 1 month ago

I'm not sure I understand your question. Do you mean that your only observations are RGB images? You will need to update the corresponding config file to reflect this and then train a policy. The policy + config will then be able to complete inference when given the appropriate observations, as in our example notebook.

PredyDaddy commented 1 month ago

I'm not sure I understand your question. Do you mean that your only observations are RGB images? You will need to update the corresponding config file to reflect this and then train a policy. The policy + config will then be able to complete inference when given the appropriate observations, as in our example notebook.

Thanks