zijian2022
/

act_d1_aug

Model card Files Files and versions

act_d1_aug

ACT policy trained for 30000 steps.

Dataset: zijian2022/fanuc_er4ia_stack_red_on_blue_d1_fixwrist
Image augmentation: enabled
chunk_size: 40
n_action_steps: 40
batch_size: 16
Checkpoint: step 30000

Downloads last month: 3

Safetensors

Model size

51.6M params

Tensor type

F32

·

Video Preview

loading

Dataset used to train zijian2022/act_d1_aug