Zhuoheng Li

Hi guys😊, Can I add my new policy to CALVIN benchmark? On ABC->D, my policy is current SOTA (average length ~3.55). I have not tested ABCD->D yet but I can...

Would you like to set up an online leaderboard for SOTA methods on libero?

1

Hello @Cranial-XIX @liuzuxin @zhuyifengzju , Would you like to set up an online leaderboard for SOTA methods on libero? That's will be very convinient for researchers to follow useful methods...

You simply cache all data in memory, it does not support larger dataset

3

### Feature request / 功能建议 It seems that you simply cache all data in the CPU memory. If I try to finetune the model on a larger dataset, I will...

Provide more information to the user

10

1. remove abbreviations and use "longer names" in logs 2. enable progress bar for evaluation by default 3. enable asynchronized env by default 4. add readme intro for resuming training

[Feature request] Is it possible to add images to videos in a stream, and avoid converting them to png first?

1

Hello @Cadene , When transfering other dataset formats to LeRobot dataset, the current approach is actually first converting all images into png, and then converting all pngs into mp4 video...

## What this does add florence+linear action head policy, and adapt it to pusht env ## How to checkout & try? (for the reviewer) Examples: ``` pip install -e ".[florence]"...

Sometimes all actions are pad in the dataset

1

### System Info ```Shell newest lerobot ``` ### Information - [ ] One of the scripts in the examples/ folder of LeRobot - [X] My own task or dataset (give...

Diffusion Policy in vqbet paper has lower performance than the diffusion policy paper

5

Hi @jayLEE0301, Thank you for sharing this work! I have a small question about the result... Table 2 computes the intersection of area IoU in the pusht task (this metric...

Would you like to release the training code?

1

It's a great work! Thank you for making it open-source! Would you like to release the training/finetuning code?