then we apply our stats which expect images to be in the range [0,255].
This bug only affects tdmpc which uses image keys during its normalization:
in_keys = [("observation", "state"), ("action")]
if cfg.policy.name == "tdmpc":
# TODO(rcadene): we add img_keys to the keys to normalize for tdmpc only, since diffusion and act policies normalize the image inside the model for now
in_keys += img_keys
# TODO(racdene): since we use next observations in tdmpc, we also add them to the normalization. We are wasting a bit of compute on this for now.
in_keys += [("next", *key) for key in img_keys]
in_keys.append(("next", "observation", "state"))
We compute stats on raw data. For instance:
However, in
lerobot/common/datasets/factory.py
we apply a first transform to modify the pixel range of images from [0,255] to [0,1]:then we apply our stats which expect images to be in the range [0,255].
This bug only affects
tdmpc
which uses image keys during its normalization:cc @alexander-soare @aliberts @qgallouedec