update readme
Browse files
README.md
CHANGED
|
@@ -4,7 +4,13 @@ datasets:
|
|
| 4 |
pipeline_tag: robotics
|
| 5 |
---
|
| 6 |
|
| 7 |
-
This model has been trained on a larger version of the commabody dataset.
|
| 8 |
It includes a [vqgan](https://github.com/CompVis/taming-transformers) encoder/decoder fine tuned from imagenet. It compresses images of size 160x256 to 10x16 tokens.
|
| 9 |
|
| 10 |
-
It also includes a GPT2 model trained to predict the next frame, wheel speeds and actions. It can be used either as a simulator or as a policy.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
pipeline_tag: robotics
|
| 5 |
---
|
| 6 |
|
| 7 |
+
This model has been trained on a larger version (194 minutes total) of the commabody dataset.
|
| 8 |
It includes a [vqgan](https://github.com/CompVis/taming-transformers) encoder/decoder fine tuned from imagenet. It compresses images of size 160x256 to 10x16 tokens.
|
| 9 |
|
| 10 |
+
It also includes a GPT2 model trained to predict the next frame, wheel speeds and actions. It can be used either as a simulator or as a policy.
|
| 11 |
+
|
| 12 |
+
<video title="imagined rollouts from 3s of context" controls>
|
| 13 |
+
<source src="https://blog.comma.ai/img/body_patrol/rollouts.webm" type="video/webm">
|
| 14 |
+
</video>
|
| 15 |
+
|
| 16 |
+
You can run it on a comma body using [our example script in body-jim](https://github.com/commaai/body-jim/blob/master/examples/roam.py).
|