镜像自地址
https://github.com/MINT-SJTU/Evo-RL.git
已同步 2026-11-21 02:27:04 +00:00
feat(logging): add swanlab backend for training runs (#17)
* feat(logging): add swanlab backend + evo1 stage2 optimizations - Add SwanLab logging support (auto-selects when SWANLAB_API_KEY is set) - Add stage2 training optimizations: tensor fastpath, gradient checkpointing - Document stage2 config override behavior and runnable value-model alternative Cherry-picked from:bfdc28c,bcecabb* refactor(logging): separate SwanLabLogger from WandBLogger - Restore WandBLogger to its original clean form with all comments - Add SwanLabLogger as a separate class with the same interface - Add make_logger() factory function to select backend based on SWANLAB_API_KEY environment variable - Move evo1 stage2 runtime logging from lerobot_train.py into EVO1Policy.__init__ where it belongs - Add ImportError handling for swanlab dependency * fix(logging): gracefully fall back to WandB when swanlab is not installed If SWANLAB_API_KEY is set but the swanlab package is not installed, make_logger() now logs a warning and falls back to WandBLogger instead of crashing with an ImportError at training startup. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Elvinyk <223015152@link.cuhk.edu.cn> Co-authored-by: MrBlue0632 <2028207642@qq.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
这个提交包含在:
@ -33,6 +33,26 @@ Validated in this repo / recent experiments:
|
|||||||
- `training_stage=stage2` finetunes both the VLM and the action head.
|
- `training_stage=stage2` finetunes both the VLM and the action head.
|
||||||
- In this repo, `resume_pretrain=true` is the Evo1-style stage handoff: load weights only, but start a fresh optimizer/scheduler state.
|
- In this repo, `resume_pretrain=true` is the Evo1-style stage handoff: load weights only, but start a fresh optimizer/scheduler state.
|
||||||
- We currently recommend `dataset.image_transforms.enable=false` in the validated training commands because the image augmentation pipeline was not stable in the tested environment.
|
- We currently recommend `dataset.image_transforms.enable=false` in the validated training commands because the image augmentation pipeline was not stable in the tested environment.
|
||||||
|
- Stage2 now defaults to `embedder_tensor_fastpath=true`, `enable_vlm_gradient_checkpointing=true`, and
|
||||||
|
`gradient_checkpointing_use_reentrant=false`.
|
||||||
|
- When stage2 is launched from `--policy.path=<stage1_ckpt>`, the stage1 checkpoint config is loaded first.
|
||||||
|
In practice, it is safer to explicitly pass the stage2 memory/speed flags on the CLI so they override any
|
||||||
|
stage1-era values saved in `config.json`.
|
||||||
|
|
||||||
|
## Optimization Summary
|
||||||
|
|
||||||
|
The current Evo1 integration includes a small set of stage2-oriented training optimizations merged from the Evo_2 branch while preserving the LeRobot/Evo-RL structure:
|
||||||
|
|
||||||
|
- Runtime config switches were added for `embedder_tensor_fastpath`, `enable_vlm_gradient_checkpointing`, and `gradient_checkpointing_use_reentrant`.
|
||||||
|
- Evo1 image collection during training no longer forces a `GPU -> CPU -> GPU` round trip before the VLM embedder.
|
||||||
|
- InternVL3 stage2 now enables a more memory-friendly checkpointing path and disables `use_cache` when checkpointing is active.
|
||||||
|
- The main `lerobot_train` entrypoint was kept intact; only lightweight Evo1 stage2 runtime logging was added.
|
||||||
|
- These Evo1-specific optimizations apply to `stage2` training and to the final `RL policy train` stage when it uses
|
||||||
|
`policy.type=evo1` with `training_stage=stage2`. They do not apply to `value-train` or `value-infer`, which use
|
||||||
|
the separate value-model pipeline.
|
||||||
|
- In the current local environment, the default `pistar06` language backbone `google/gemma-3-270m` may fail with
|
||||||
|
a gated-repo `403`. For runnable value/RL scripts, prefer explicitly setting
|
||||||
|
`--value.language_repo_id=Qwen/Qwen2.5-0.5B`.
|
||||||
|
|
||||||
## Stage 1 Command
|
## Stage 1 Command
|
||||||
|
|
||||||
@ -89,6 +109,10 @@ PYTHONPATH=src /opt/conda/bin/accelerate launch \
|
|||||||
--resume_pretrain=true \
|
--resume_pretrain=true \
|
||||||
--policy.vlm_model_name=/root/private_data/models/InternVL3-1B \
|
--policy.vlm_model_name=/root/private_data/models/InternVL3-1B \
|
||||||
--policy.device=cuda \
|
--policy.device=cuda \
|
||||||
|
--policy.use_flash_attn=true \
|
||||||
|
--policy.embedder_tensor_fastpath=true \
|
||||||
|
--policy.enable_vlm_gradient_checkpointing=true \
|
||||||
|
--policy.gradient_checkpointing_use_reentrant=false \
|
||||||
--policy.push_to_hub=false \
|
--policy.push_to_hub=false \
|
||||||
--policy.dropout=0.2 \
|
--policy.dropout=0.2 \
|
||||||
--policy.optimizer_lr=1e-5 \
|
--policy.optimizer_lr=1e-5 \
|
||||||
|
|||||||
@ -56,6 +56,9 @@ class Evo1Config(PreTrainedConfig):
|
|||||||
vlm_num_layers: int | None = 14
|
vlm_num_layers: int | None = 14
|
||||||
vlm_dtype: str = "bfloat16"
|
vlm_dtype: str = "bfloat16"
|
||||||
use_flash_attn: bool = True
|
use_flash_attn: bool = True
|
||||||
|
embedder_tensor_fastpath: bool = True
|
||||||
|
enable_vlm_gradient_checkpointing: bool | None = None
|
||||||
|
gradient_checkpointing_use_reentrant: bool = False
|
||||||
action_head: str = "flowmatching"
|
action_head: str = "flowmatching"
|
||||||
embed_dim: int = 896
|
embed_dim: int = 896
|
||||||
hidden_dim: int = 1024
|
hidden_dim: int = 1024
|
||||||
@ -97,6 +100,9 @@ class Evo1Config(PreTrainedConfig):
|
|||||||
self.finetune_vlm = True
|
self.finetune_vlm = True
|
||||||
self.finetune_action_head = True
|
self.finetune_action_head = True
|
||||||
|
|
||||||
|
if self.enable_vlm_gradient_checkpointing is None:
|
||||||
|
self.enable_vlm_gradient_checkpointing = self.training_stage == "stage2"
|
||||||
|
|
||||||
if self.n_action_steps > self.chunk_size:
|
if self.n_action_steps > self.chunk_size:
|
||||||
raise ValueError(
|
raise ValueError(
|
||||||
f"n_action_steps ({self.n_action_steps}) must be <= chunk_size ({self.chunk_size})"
|
f"n_action_steps ({self.n_action_steps}) must be <= chunk_size ({self.chunk_size})"
|
||||||
|
|||||||
@ -22,6 +22,9 @@ class EVO1(nn.Module):
|
|||||||
num_language_layers=config.get("vlm_num_layers", 14),
|
num_language_layers=config.get("vlm_num_layers", 14),
|
||||||
model_dtype=config.get("vlm_dtype", "bfloat16"),
|
model_dtype=config.get("vlm_dtype", "bfloat16"),
|
||||||
use_flash_attn=config.get("use_flash_attn", True),
|
use_flash_attn=config.get("use_flash_attn", True),
|
||||||
|
enable_gradient_checkpointing=config.get("enable_vlm_gradient_checkpointing", False),
|
||||||
|
enable_tensor_fastpath=config.get("embedder_tensor_fastpath", True),
|
||||||
|
gradient_checkpointing_use_reentrant=config.get("gradient_checkpointing_use_reentrant", False),
|
||||||
)
|
)
|
||||||
|
|
||||||
action_head_type = config.get("action_head", "flowmatching").lower()
|
action_head_type = config.get("action_head", "flowmatching").lower()
|
||||||
|
|||||||
@ -88,12 +88,18 @@ class InternVL3Embedder(nn.Module):
|
|||||||
num_language_layers: int | None = 14,
|
num_language_layers: int | None = 14,
|
||||||
model_dtype: str | torch.dtype = "bfloat16",
|
model_dtype: str | torch.dtype = "bfloat16",
|
||||||
use_flash_attn: bool = True,
|
use_flash_attn: bool = True,
|
||||||
|
enable_gradient_checkpointing: bool = False,
|
||||||
|
enable_tensor_fastpath: bool = True,
|
||||||
|
gradient_checkpointing_use_reentrant: bool = False,
|
||||||
):
|
):
|
||||||
super().__init__()
|
super().__init__()
|
||||||
self._requested_device = device
|
self._requested_device = device
|
||||||
self.image_size = image_size
|
self.image_size = image_size
|
||||||
self.num_language_layers = num_language_layers
|
self.num_language_layers = num_language_layers
|
||||||
self.max_text_length = 1024 # InternVL3 supports up to 1024 tokens
|
self.max_text_length = 1024 # InternVL3 supports up to 1024 tokens
|
||||||
|
self.enable_gradient_checkpointing = bool(enable_gradient_checkpointing)
|
||||||
|
self.enable_tensor_fastpath = bool(enable_tensor_fastpath)
|
||||||
|
self.gradient_checkpointing_use_reentrant = bool(gradient_checkpointing_use_reentrant)
|
||||||
self.transform = build_transform(image_size)
|
self.transform = build_transform(image_size)
|
||||||
self.tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, use_fast=False)
|
self.tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, use_fast=False)
|
||||||
if isinstance(model_dtype, str):
|
if isinstance(model_dtype, str):
|
||||||
@ -123,12 +129,53 @@ class InternVL3Embedder(nn.Module):
|
|||||||
else:
|
else:
|
||||||
self.model.language_model.layers = torch.nn.ModuleList(layers)
|
self.model.language_model.layers = torch.nn.ModuleList(layers)
|
||||||
self.model.language_model.lm_head = torch.nn.Identity()
|
self.model.language_model.lm_head = torch.nn.Identity()
|
||||||
|
self._configure_memory_features()
|
||||||
if hasattr(self.model, "vision_model") and hasattr(self.model.vision_model, "encoder"):
|
|
||||||
self.model.vision_model.encoder.gradient_checkpointing = False
|
|
||||||
|
|
||||||
self.img_context_token_id = self.tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
|
self.img_context_token_id = self.tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
|
||||||
|
|
||||||
|
def _configure_memory_features(self) -> None:
|
||||||
|
checkpoint_kwargs = {"use_reentrant": self.gradient_checkpointing_use_reentrant}
|
||||||
|
|
||||||
|
def _enable_ckpt(module) -> bool:
|
||||||
|
if module is None or not hasattr(module, "gradient_checkpointing_enable"):
|
||||||
|
return False
|
||||||
|
module.gradient_checkpointing_enable(gradient_checkpointing_kwargs=checkpoint_kwargs)
|
||||||
|
return True
|
||||||
|
|
||||||
|
if not self.enable_gradient_checkpointing:
|
||||||
|
if hasattr(self.model, "vision_model") and hasattr(self.model.vision_model, "encoder"):
|
||||||
|
self.model.vision_model.encoder.gradient_checkpointing = False
|
||||||
|
return
|
||||||
|
|
||||||
|
enabled_any = False
|
||||||
|
enabled_any = _enable_ckpt(self.model) or enabled_any
|
||||||
|
|
||||||
|
if hasattr(self.model, "vision_model") and hasattr(self.model.vision_model, "encoder"):
|
||||||
|
self.model.vision_model.encoder.gradient_checkpointing = True
|
||||||
|
enabled_any = True
|
||||||
|
|
||||||
|
if hasattr(self.model, "language_model"):
|
||||||
|
language_model = self.model.language_model
|
||||||
|
enabled_any = _enable_ckpt(language_model) or enabled_any
|
||||||
|
if hasattr(language_model, "model"):
|
||||||
|
enabled_any = _enable_ckpt(language_model.model) or enabled_any
|
||||||
|
if hasattr(language_model, "config"):
|
||||||
|
language_model.config.use_cache = False
|
||||||
|
|
||||||
|
if hasattr(self.model, "config"):
|
||||||
|
self.model.config.use_cache = False
|
||||||
|
|
||||||
|
if hasattr(self.model, "enable_input_require_grads"):
|
||||||
|
self.model.enable_input_require_grads()
|
||||||
|
|
||||||
|
if enabled_any:
|
||||||
|
logging.info(
|
||||||
|
"Enabled InternVL3 gradient checkpointing (use_reentrant=%s).",
|
||||||
|
self.gradient_checkpointing_use_reentrant,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
logging.warning("Requested InternVL3 gradient checkpointing, but no checkpointable module was found.")
|
||||||
|
|
||||||
def _dynamic_preprocess_tensor(
|
def _dynamic_preprocess_tensor(
|
||||||
self, image_t, min_num=1, max_num=1, use_thumbnail=False
|
self, image_t, min_num=1, max_num=1, use_thumbnail=False
|
||||||
):
|
):
|
||||||
@ -191,7 +238,7 @@ class InternVL3Embedder(nn.Module):
|
|||||||
for image_tensors in image_tensors_batch:
|
for image_tensors in image_tensors_batch:
|
||||||
num_tiles_list = []
|
num_tiles_list = []
|
||||||
for image in image_tensors:
|
for image in image_tensors:
|
||||||
if isinstance(image, torch.Tensor):
|
if isinstance(image, torch.Tensor) and self.enable_tensor_fastpath:
|
||||||
if (
|
if (
|
||||||
image.ndim == 3
|
image.ndim == 3
|
||||||
and image.shape[0] == 3
|
and image.shape[0] == 3
|
||||||
@ -216,6 +263,8 @@ class InternVL3Embedder(nn.Module):
|
|||||||
tiles = self._dynamic_preprocess_tensor(image_t)
|
tiles = self._dynamic_preprocess_tensor(image_t)
|
||||||
tile_tensors = (tiles - mean) / std
|
tile_tensors = (tiles - mean) / std
|
||||||
else:
|
else:
|
||||||
|
if isinstance(image, torch.Tensor):
|
||||||
|
image = to_pil_image(image.detach().to(device="cpu"))
|
||||||
image_t = TF.to_tensor(image).to(device=self.device, dtype=torch.float32)
|
image_t = TF.to_tensor(image).to(device=self.device, dtype=torch.float32)
|
||||||
tiles = self._dynamic_preprocess_tensor(image_t)
|
tiles = self._dynamic_preprocess_tensor(image_t)
|
||||||
tile_tensors = (tiles - mean) / std
|
tile_tensors = (tiles - mean) / std
|
||||||
|
|||||||
@ -1,4 +1,5 @@
|
|||||||
import builtins
|
import builtins
|
||||||
|
import logging
|
||||||
from collections import deque
|
from collections import deque
|
||||||
from contextlib import nullcontext
|
from contextlib import nullcontext
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
@ -29,6 +30,16 @@ class EVO1Policy(PreTrainedPolicy):
|
|||||||
self.config = config
|
self.config = config
|
||||||
self.model = EVO1(self._build_model_config(config))
|
self.model = EVO1(self._build_model_config(config))
|
||||||
self.model.set_finetune_flags()
|
self.model.set_finetune_flags()
|
||||||
|
|
||||||
|
if config.training_stage == "stage2":
|
||||||
|
logging.info(
|
||||||
|
"Evo1 stage2 runtime settings: embedder_tensor_fastpath=%s "
|
||||||
|
"enable_vlm_gradient_checkpointing=%s gradient_checkpointing_use_reentrant=%s",
|
||||||
|
config.embedder_tensor_fastpath,
|
||||||
|
config.enable_vlm_gradient_checkpointing,
|
||||||
|
config.gradient_checkpointing_use_reentrant,
|
||||||
|
)
|
||||||
|
|
||||||
self.reset()
|
self.reset()
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
@ -70,6 +81,9 @@ class EVO1Policy(PreTrainedPolicy):
|
|||||||
"vlm_num_layers": config.vlm_num_layers,
|
"vlm_num_layers": config.vlm_num_layers,
|
||||||
"vlm_dtype": config.vlm_dtype,
|
"vlm_dtype": config.vlm_dtype,
|
||||||
"use_flash_attn": config.use_flash_attn,
|
"use_flash_attn": config.use_flash_attn,
|
||||||
|
"embedder_tensor_fastpath": config.embedder_tensor_fastpath,
|
||||||
|
"enable_vlm_gradient_checkpointing": config.enable_vlm_gradient_checkpointing,
|
||||||
|
"gradient_checkpointing_use_reentrant": config.gradient_checkpointing_use_reentrant,
|
||||||
"action_head": config.action_head,
|
"action_head": config.action_head,
|
||||||
"action_horizon": config.chunk_size,
|
"action_horizon": config.chunk_size,
|
||||||
"per_action_dim": config.max_action_dim,
|
"per_action_dim": config.max_action_dim,
|
||||||
@ -300,7 +314,7 @@ class EVO1Policy(PreTrainedPolicy):
|
|||||||
raise ValueError(
|
raise ValueError(
|
||||||
f"EVO1 batch mismatch across cameras: key={camera_key} batch={image.shape[0]} expected={batch_size}"
|
f"EVO1 batch mismatch across cameras: key={camera_key} batch={image.shape[0]} expected={batch_size}"
|
||||||
)
|
)
|
||||||
sample_images.append(image[batch_index].detach().cpu())
|
sample_images.append(image[batch_index])
|
||||||
if not sample_images:
|
if not sample_images:
|
||||||
raise ValueError("EVO1 received a batch without any image tensor.")
|
raise ValueError("EVO1 received a batch without any image tensor.")
|
||||||
while len(sample_images) < self.config.max_views:
|
while len(sample_images) < self.config.max_views:
|
||||||
|
|||||||
@ -150,13 +150,11 @@ def train(cfg: TrainRLServerPipelineConfig, job_name: str | None = None):
|
|||||||
logging.info(f"Learner logging initialized, writing to {log_file}")
|
logging.info(f"Learner logging initialized, writing to {log_file}")
|
||||||
logging.info(pformat(cfg.to_dict()))
|
logging.info(pformat(cfg.to_dict()))
|
||||||
|
|
||||||
# Setup WandB logging if enabled
|
# Setup logging
|
||||||
if cfg.wandb.enable and cfg.wandb.project:
|
from lerobot.rl.wandb_utils import make_logger
|
||||||
from lerobot.rl.wandb_utils import WandBLogger
|
|
||||||
|
|
||||||
wandb_logger = WandBLogger(cfg)
|
wandb_logger = make_logger(cfg)
|
||||||
else:
|
if wandb_logger is None:
|
||||||
wandb_logger = None
|
|
||||||
logging.info(colored("Logs will be saved locally.", "yellow", attrs=["bold"]))
|
logging.info(colored("Logs will be saved locally.", "yellow", attrs=["bold"]))
|
||||||
|
|
||||||
# Handle resume logic
|
# Handle resume logic
|
||||||
|
|||||||
@ -201,3 +201,106 @@ class WandBLogger:
|
|||||||
|
|
||||||
wandb_video = self._wandb.Video(video_path, fps=self.env_fps, format="mp4")
|
wandb_video = self._wandb.Video(video_path, fps=self.env_fps, format="mp4")
|
||||||
self._wandb.log({f"{mode}/video": wandb_video}, step=step)
|
self._wandb.log({f"{mode}/video": wandb_video}, step=step)
|
||||||
|
|
||||||
|
|
||||||
|
class SwanLabLogger:
|
||||||
|
"""A helper class to log training metrics using SwanLab."""
|
||||||
|
|
||||||
|
def __init__(self, cfg: TrainPipelineConfig):
|
||||||
|
try:
|
||||||
|
import swanlab
|
||||||
|
except ImportError:
|
||||||
|
raise ImportError(
|
||||||
|
"SwanLab is required when SWANLAB_API_KEY is set. "
|
||||||
|
"Install it with: pip install swanlab"
|
||||||
|
)
|
||||||
|
|
||||||
|
self.cfg = cfg.wandb
|
||||||
|
self.log_dir = cfg.output_dir
|
||||||
|
self.job_name = cfg.job_name
|
||||||
|
self.env_fps = cfg.env.fps if cfg.env else None
|
||||||
|
|
||||||
|
swanlab.login(api_key=os.environ["SWANLAB_API_KEY"])
|
||||||
|
self._run = swanlab.init(
|
||||||
|
project=self.cfg.project,
|
||||||
|
workspace=self.cfg.entity,
|
||||||
|
experiment_name=self.job_name,
|
||||||
|
description=self.cfg.notes,
|
||||||
|
tags=cfg_to_group(cfg, return_list=True, truncate_tags=True),
|
||||||
|
logdir=str(self.log_dir),
|
||||||
|
config=cfg.to_dict(),
|
||||||
|
mode=self.cfg.mode if self.cfg.mode in ["offline", "disabled"] else "cloud",
|
||||||
|
id=cfg.wandb.run_id,
|
||||||
|
resume="must" if cfg.resume else None,
|
||||||
|
)
|
||||||
|
run_id = getattr(self._run, "id", None)
|
||||||
|
cfg.wandb.run_id = run_id
|
||||||
|
logging.info(colored("Logs will be synced with swanlab.", "blue", attrs=["bold"]))
|
||||||
|
try:
|
||||||
|
import swanlab.data as swanlab_data
|
||||||
|
|
||||||
|
run_url = swanlab_data.get_url()
|
||||||
|
if run_url:
|
||||||
|
logging.info(f"Track this run --> {colored(run_url, 'yellow', attrs=['bold'])}")
|
||||||
|
except Exception:
|
||||||
|
pass
|
||||||
|
|
||||||
|
def log_policy(self, checkpoint_dir: Path):
|
||||||
|
return
|
||||||
|
|
||||||
|
def log_dict(
|
||||||
|
self, d: dict, step: int | None = None, mode: str = "train", custom_step_key: str | None = None
|
||||||
|
):
|
||||||
|
if mode not in {"train", "eval"}:
|
||||||
|
raise ValueError(mode)
|
||||||
|
if step is None and custom_step_key is None:
|
||||||
|
raise ValueError("Either step or custom_step_key must be provided.")
|
||||||
|
|
||||||
|
data = {}
|
||||||
|
if custom_step_key is not None and custom_step_key in d:
|
||||||
|
value_custom_step = d[custom_step_key]
|
||||||
|
data[f"{mode}/{custom_step_key}"] = value_custom_step
|
||||||
|
if step is None:
|
||||||
|
step = int(value_custom_step)
|
||||||
|
for k, v in d.items():
|
||||||
|
if not isinstance(v, (int | float | str)):
|
||||||
|
logging.warning(
|
||||||
|
f'SwanLab logging of key "{k}" was ignored as its type "{type(v)}" is not handled by this wrapper.'
|
||||||
|
)
|
||||||
|
continue
|
||||||
|
if custom_step_key is not None and k == custom_step_key:
|
||||||
|
continue
|
||||||
|
data[f"{mode}/{k}"] = v
|
||||||
|
if data:
|
||||||
|
self._run.log(data, step=step)
|
||||||
|
|
||||||
|
def log_video(self, video_path: str, step: int, mode: str = "train"):
|
||||||
|
if mode not in {"train", "eval"}:
|
||||||
|
raise ValueError(mode)
|
||||||
|
|
||||||
|
try:
|
||||||
|
import swanlab
|
||||||
|
|
||||||
|
self._run.log({f"{mode}/video": swanlab.Video(video_path)}, step=step)
|
||||||
|
except Exception as exc:
|
||||||
|
logging.warning("Failed to log video to SwanLab: %s", exc)
|
||||||
|
|
||||||
|
|
||||||
|
def make_logger(cfg: TrainPipelineConfig) -> WandBLogger | SwanLabLogger | None:
|
||||||
|
"""Create a training logger based on config and environment.
|
||||||
|
|
||||||
|
Returns SwanLabLogger if SWANLAB_API_KEY is set, WandBLogger otherwise.
|
||||||
|
Returns None if logging is disabled.
|
||||||
|
"""
|
||||||
|
if not (cfg.wandb.enable and cfg.wandb.project):
|
||||||
|
return None
|
||||||
|
|
||||||
|
if os.getenv("SWANLAB_API_KEY"):
|
||||||
|
try:
|
||||||
|
return SwanLabLogger(cfg)
|
||||||
|
except ImportError:
|
||||||
|
logging.warning(
|
||||||
|
"swanlab package is not installed but SWANLAB_API_KEY is set. "
|
||||||
|
"Falling back to WandB. Install swanlab with: pip install swanlab"
|
||||||
|
)
|
||||||
|
return WandBLogger(cfg)
|
||||||
|
|||||||
@ -37,7 +37,7 @@ from lerobot.policies.factory import make_policy, make_pre_post_processors
|
|||||||
from lerobot.policies.pretrained import PreTrainedPolicy
|
from lerobot.policies.pretrained import PreTrainedPolicy
|
||||||
from lerobot.rl.acp_dataset_stats import compute_acp_indicator_stats
|
from lerobot.rl.acp_dataset_stats import compute_acp_indicator_stats
|
||||||
from lerobot.rl.acp_hook import build_acp_raw_batch_hook
|
from lerobot.rl.acp_hook import build_acp_raw_batch_hook
|
||||||
from lerobot.rl.wandb_utils import WandBLogger
|
from lerobot.rl.wandb_utils import make_logger
|
||||||
from lerobot.scripts.lerobot_eval import eval_policy_all
|
from lerobot.scripts.lerobot_eval import eval_policy_all
|
||||||
from lerobot.utils.import_utils import register_third_party_plugins
|
from lerobot.utils.import_utils import register_third_party_plugins
|
||||||
from lerobot.utils.logging_utils import AverageMeter, MetricsTracker
|
from lerobot.utils.logging_utils import AverageMeter, MetricsTracker
|
||||||
@ -200,13 +200,10 @@ def train(
|
|||||||
if is_main_process:
|
if is_main_process:
|
||||||
logging.info(pformat(cfg.to_dict()))
|
logging.info(pformat(cfg.to_dict()))
|
||||||
|
|
||||||
# Initialize wandb only on main process
|
# Initialize logger only on main process
|
||||||
if cfg.wandb.enable and cfg.wandb.project and is_main_process:
|
wandb_logger = make_logger(cfg) if is_main_process else None
|
||||||
wandb_logger = WandBLogger(cfg)
|
if wandb_logger is None and is_main_process:
|
||||||
else:
|
logging.info(colored("Logs will be saved locally.", "yellow", attrs=["bold"]))
|
||||||
wandb_logger = None
|
|
||||||
if is_main_process:
|
|
||||||
logging.info(colored("Logs will be saved locally.", "yellow", attrs=["bold"]))
|
|
||||||
|
|
||||||
if cfg.seed is not None:
|
if cfg.seed is not None:
|
||||||
set_seed(cfg.seed, accelerator=accelerator)
|
set_seed(cfg.seed, accelerator=accelerator)
|
||||||
|
|||||||
@ -18,7 +18,7 @@ from lerobot.datasets.utils import cycle
|
|||||||
from lerobot.optim.factory import make_optimizer_and_scheduler
|
from lerobot.optim.factory import make_optimizer_and_scheduler
|
||||||
from lerobot.policies.factory import make_policy, make_pre_post_processors
|
from lerobot.policies.factory import make_policy, make_pre_post_processors
|
||||||
from lerobot.policies.pretrained import PreTrainedPolicy
|
from lerobot.policies.pretrained import PreTrainedPolicy
|
||||||
from lerobot.rl.wandb_utils import WandBLogger
|
from lerobot.rl.wandb_utils import make_logger
|
||||||
from lerobot.utils.import_utils import register_third_party_plugins
|
from lerobot.utils.import_utils import register_third_party_plugins
|
||||||
from lerobot.utils.logging_utils import AverageMeter, MetricsTracker
|
from lerobot.utils.logging_utils import AverageMeter, MetricsTracker
|
||||||
from lerobot.utils.random_utils import set_seed
|
from lerobot.utils.random_utils import set_seed
|
||||||
@ -98,12 +98,9 @@ def value_train(
|
|||||||
if is_main_process:
|
if is_main_process:
|
||||||
logging.info(pformat(cfg.to_dict()))
|
logging.info(pformat(cfg.to_dict()))
|
||||||
|
|
||||||
if cfg.wandb.enable and cfg.wandb.project and is_main_process:
|
wandb_logger = make_logger(cfg) if is_main_process else None
|
||||||
wandb_logger = WandBLogger(cfg)
|
if wandb_logger is None and is_main_process:
|
||||||
else:
|
logging.info(colored("Logs will be saved locally.", "yellow", attrs=["bold"]))
|
||||||
wandb_logger = None
|
|
||||||
if is_main_process:
|
|
||||||
logging.info(colored("Logs will be saved locally.", "yellow", attrs=["bold"]))
|
|
||||||
|
|
||||||
if cfg.seed is not None:
|
if cfg.seed is not None:
|
||||||
set_seed(cfg.seed, accelerator=accelerator)
|
set_seed(cfg.seed, accelerator=accelerator)
|
||||||
|
|||||||
在新工单中引用
屏蔽一个用户