Views
No views yet
dit_policy) action-chunking Transformer for a DG-5F dexterous hand + UR5e arm
blue-cable manipulation task. The two GelSight tactile cameras are encoded by a frozen
SPARSH (facebook/sparsh-dino-base) tactile encoder; the two RealSense RGB cameras use a
vit_base backbone.Kaz55/dg5f_ur5e_bluecable60ep_h5
(60 episodes). This repo contains the final checkpoint at 50,000 iterations.| File | Description |
|---|---|
dg5f_bluecable60_sparsh_ac90_50000.pth | Model weights @ 50k iters (≈3.5 GB) |
agent_config.yaml | Agent architecture config (needed to rebuild the model) |
exp_config.yaml | Full experiment config |
hydra/config.yaml, hydra/overrides.yaml | Resolved Hydra config + CLI overrides |
combined_ac_norm.json, combined_state_norm.json | Action / state normalization stats (required for inference) |
train_data_bluecable60_ac_norm.json, train_data_bluecable60_state_norm.json | Per-dataset norm stats |
The.pthalone is not enough to run the policy — you also needagent_config.yamland the*_norm.jsonnormalization statistics.
realsense, realsense2 → RGB vit_base; gelsight1, gelsight2 → SPARSH, cam indices [2, 3]).ac_chunk): 90sparsh-dino-base, in_chans=6 (2 bg-subtracted frames), pooling=register, frozen.| Framework | DexWild dit_policy (data4robotics), accelerate bf16, single GPU |
| Agent / task | agent=transformer_sparsh, task=rdm_dg5f_sparsh |
| Iterations | 50,000 (save_freq/keep_freq=10,000) |
| Batch size | 32 |
| LR / sched | 1e-4, trainer=bc_cos_sched (cosine) |
| RGB backbone | vit_base (SOUP_1M_DH.pth) |
use_lang / use_tactile (uSkin) | false / false (GelSight routed through SPARSH, not uSkin) |