BIue-Jay commited on
Commit
33dd4ce
·
verified ·
1 Parent(s): 599e346

Update model card (task / checkpoint table)

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -57,7 +57,7 @@ scheduler / RNG / DeepSpeed resume state is not. `code/` holds the adapter code
57
 
58
  Model inputs are identical across all benchmark models: G1 state 44-D (29 body joint angles + 6 + 6 measured hand values
59
  + 3 projected gravity), H2 state 78-D (75 joint angles + 3 projected gravity), no joint velocities. Cameras: G1 ego view +
60
- chest; H2 head + chest (A14: head + chest + wrist). The third-person camera recorded in the datasets is for data review
61
  only and is never a model input. Each camera is a separate image input, except for Delta Flow and DiT4DiT, which
62
  place the views side by side in one frame.
63
  Training uses the Humanoid Benchmark online data augmentation spec v2 (15 photometric / geometric / sensor / lighting
 
57
 
58
  Model inputs are identical across all benchmark models: G1 state 44-D (29 body joint angles + 6 + 6 measured hand values
59
  + 3 projected gravity), H2 state 78-D (75 joint angles + 3 projected gravity), no joint velocities. Cameras: G1 ego view +
60
+ chest; H2 head + chest (the 3-camera re-trains of 2026-11-12/13 also used the right-wrist camera; the `protocol.json` of each folder lists its cameras). The third-person camera recorded in the datasets is for data review
61
  only and is never a model input. Each camera is a separate image input, except for Delta Flow and DiT4DiT, which
62
  place the views side by side in one frame.
63
  Training uses the Humanoid Benchmark online data augmentation spec v2 (15 photometric / geometric / sensor / lighting