Files
lerobot-clone/src/lerobot
Pepijn fcdae0ce8e chore(smolvla2-runtime): tensor-level obs print for both inference paths
Helper that prints (once per provider lifetime) every
``observation.*`` tensor the policy is about to see, with its shape,
dtype, device, and per-channel min/max/mean/std. Wired into both the
dry-run dataset path and the live-robot path.

Now we can bisect train/inference mismatch *at the tensor level* —
if the same checkpoint produces coherent text on one path's tensors
and ``\n`` on the other's, and the printed tensor stats differ
materially, the bug is in the observation prep, not in the model or
the training distribution.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 18:19:18 +02:00
..