wangzixiang
/
lerobot
mirror of https://github.com/huggingface/lerobot.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Override pretrained model config (#147)

This commit is contained in:
Alexander Soare 2024-05-08 12:56:21 +01:00 committed by GitHub
parent 26d9a070d8
commit 47de07658c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 14 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
lerobot/common/policies/factory.py
View File

@ -1,4 +1,5 @@
import inspect
import logging
from omegaconf import DictConfig, OmegaConf
@ -8,9 +9,10 @@ from lerobot.common.utils.utils import get_safe_torch_device
def _policy_cfg_from_hydra_cfg(policy_cfg_class, hydra_cfg):
expected_kwargs = set(inspect.signature(policy_cfg_class).parameters)
assert set(hydra_cfg.policy).issuperset(
expected_kwargs
), f"Hydra config is missing arguments: {set(expected_kwargs).difference(hydra_cfg.policy)}"
if not set(hydra_cfg.policy).issuperset(expected_kwargs):
logging.warning(
f"Hydra config is missing arguments: {set(expected_kwargs).difference(hydra_cfg.policy)}"
)
policy_cfg = policy_cfg_class(
**{
k: v
@ -62,11 +64,18 @@ def make_policy(
policy_cls, policy_cfg_class = get_policy_and_config_classes(hydra_cfg.policy.name)
policy_cfg = _policy_cfg_from_hydra_cfg(policy_cfg_class, hydra_cfg)
if pretrained_policy_name_or_path is None:
policy_cfg = _policy_cfg_from_hydra_cfg(policy_cfg_class, hydra_cfg)
# Make a fresh policy.
policy = policy_cls(policy_cfg, dataset_stats)
else:
policy = policy_cls.from_pretrained(pretrained_policy_name_or_path)
# Load a pretrained policy and override the config if needed (for example, if there are inference-time
# hyperparameters that we want to vary).
# TODO(alexander-soare): This hack makes use of huggingface_hub's tooling to load the policy with, pretrained
# weights which are then loaded into a fresh policy with the desired config. This PR in huggingface_hub should
# make it possible to avoid the hack: https://github.com/huggingface/huggingface_hub/pull/2274.
policy = policy_cls(policy_cfg)
policy.load_state_dict(policy_cls.from_pretrained(pretrained_policy_name_or_path).state_dict())
policy.to(get_safe_torch_device(hydra_cfg.device))