lerobot/lerobot/common/envs/utils.py

44 lines
1.6 KiB
Python

import einops
import numpy as np
import torch
from torch import Tensor
def preprocess_observations(observations: dict[str, np.ndarray]) -> dict[str, Tensor]:
"""Convert environment observation to LeRobot format observation.
Args:
observation: Dictionary of observation batches from a Gym vector environment.
Returns:
Dictionary of observation batches with keys renamed to LeRobot format and values as tensors.
"""
# map to expected inputs for the policy
return_observations = {}
if isinstance(observations["pixels"], dict):
imgs = {f"observation.images.{key}": img for key, img in observations["pixels"].items()}
else:
imgs = {"observation.image": observations["pixels"]}
for imgkey, img in imgs.items():
img = torch.from_numpy(img)
# sanity check that images are channel last
_, h, w, c = img.shape
assert c < h and c < w, f"expect channel first images, but instead {img.shape}"
# sanity check that images are uint8
assert img.dtype == torch.uint8, f"expect torch.uint8, but instead {img.dtype=}"
# convert to channel first of type float32 in range [0,1]
img = einops.rearrange(img, "b h w c -> b c h w").contiguous()
img = img.type(torch.float32)
img /= 255
return_observations[imgkey] = img
# TODO(rcadene): enable pixels only baseline with `obs_type="pixels"` in environment by removing
# requirement for "agent_pos"
return_observations["observation.state"] = torch.from_numpy(observations["agent_pos"]).float()
return return_observations