refactor(config): Move device & amp args to PreTrainedConfig (#812)

Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
This commit is contained in:
Steven Palma
2025-03-06 17:59:28 +01:00
committed by GitHub
parent 10706ed753
commit 5e9473806c
19 changed files with 62 additions and 136 deletions

View File

@@ -12,17 +12,14 @@
# See the License for the specific language governing permissions and
# limitations under the License.
import logging
from dataclasses import dataclass
from pathlib import Path
import draccus
from lerobot.common.robot_devices.robots.configs import RobotConfig
from lerobot.common.utils.utils import auto_select_torch_device, is_amp_available, is_torch_device_available
from lerobot.configs import parser
from lerobot.configs.policies import PreTrainedConfig
from lerobot.configs.train import TrainPipelineConfig
@dataclass
@@ -57,11 +54,6 @@ class RecordControlConfig(ControlConfig):
# Root directory where the dataset will be stored (e.g. 'dataset/path').
root: str | Path | None = None
policy: PreTrainedConfig | None = None
# TODO(rcadene, aliberts): By default, use device and use_amp values from policy checkpoint.
device: str | None = None # cuda | cpu | mps
# `use_amp` determines whether to use Automatic Mixed Precision (AMP) for training and evaluation. With AMP,
# automatic gradient scaling is used.
use_amp: bool | None = None
# Limit the frames per second. By default, uses the policy fps.
fps: int | None = None
# Number of seconds before starting data collection. It allows the robot devices to warmup and synchronize.
@@ -104,27 +96,6 @@ class RecordControlConfig(ControlConfig):
self.policy = PreTrainedConfig.from_pretrained(policy_path, cli_overrides=cli_overrides)
self.policy.pretrained_path = policy_path
# When no device or use_amp are given, use the one from training config.
if self.device is None or self.use_amp is None:
train_cfg = TrainPipelineConfig.from_pretrained(policy_path)
if self.device is None:
self.device = train_cfg.device
if self.use_amp is None:
self.use_amp = train_cfg.use_amp
# Automatically switch to available device if necessary
if not is_torch_device_available(self.device):
auto_device = auto_select_torch_device()
logging.warning(f"Device '{self.device}' is not available. Switching to '{auto_device}'.")
self.device = auto_device
# Automatically deactivate AMP if necessary
if self.use_amp and not is_amp_available(self.device):
logging.warning(
f"Automatic Mixed Precision (amp) is not available on device '{self.device}'. Deactivating AMP."
)
self.use_amp = False
@ControlConfig.register_subclass("replay")
@dataclass