feat(actpred): 固定范围归一化 + 逐列加权损失，附 pybot*actpred 审计修复
新增 action_norm.py 固定物理范围 min-max 归一化，无 stats 文件零状态部署；train.py 引入 _weighted_mse 逐列加权（舵机 1.0/spk 0.2/保留位 0.0）。审计修复: P0-1 pybot 读 normalize_mode, R2-1 NaN 阻断 best, P2-a 后端大小写不敏感, P1-3 utf-8-sig BOM, R1-1 data_dir 覆盖, R2-7 _run.sh 报错, R2-3 空 val 存 best.pt, P2-a2 误报警, R1-2 合并 parse_action_history, P2-b 合并 numpy import。评估修正 oob 物理界+error_growth 按 episode 中位数。推理部署全链支持 fixed_range。
This commit is contained in:
qing committed
1 parent
adfa61aa3c
commit
85bf68f505
19 files changed
+874
-167
No files matched your search
+57
-30
@@ -33,6 +33,8 @@ from config import (Config, build_argparser, apply_overrides,
|
||||
validate_config_values, warn_init_from_mismatch)
|
||||
from model import ActionPredictor
|
||||
from mt_parser import parse_mt_directory
|
||||
from action_norm import normalize_action, default_column_weights
|
||||
from train import _weighted_mse
|
||||
|
||||
_IMAGENET_MEAN = [0.485, 0.456, 0.406]
|
||||
_IMAGENET_STD = [0.229, 0.224, 0.225]
|
||||
@@ -46,11 +48,15 @@ class MTActionDataset(Dataset):
|
||||
|
||||
def __init__(self, mt_dir: str, history_len: int, action_dim: int,
|
||||
file_indices: list = None, files: list = None,
|
||||
action_mean=None, action_std=None):
|
||||
action_mean=None, action_std=None,
|
||||
normalize_mode: str = "zscore"):
|
||||
self.history_len = history_len
|
||||
self.action_dim = action_dim
|
||||
self._action_mean = action_mean
|
||||
self._action_std = action_std
|
||||
# 固定物理范围归一化（免统计量；action_mean 传入时优先 z-score）
|
||||
self._fixed_range = (normalize_mode == "fixed_range"
|
||||
and action_mean is None)
|
||||
self.samples = []
|
||||
|
||||
# 复用调用方已解析的结果（避免 train/val 各自重复解析同一目录）
|
||||
@@ -83,6 +89,9 @@ class MTActionDataset(Dataset):
|
||||
|
||||
def __getitem__(self, idx):
|
||||
history, target = self.samples[idx]
|
||||
if self._fixed_range:
|
||||
history = normalize_action(history, self.action_dim)
|
||||
target = normalize_action(target, self.action_dim)
|
||||
history = torch.from_numpy(history.copy())
|
||||
target = torch.from_numpy(target.copy())
|
||||
if self._action_mean is not None:
|
||||
@@ -110,7 +119,7 @@ def _placeholder_images(batch, frame_len, image_height, image_width,
|
||||
def pretrain_one_epoch(model, loader, optimizer, device, image_width,
|
||||
image_height, frame_len,
|
||||
max_grad_norm=None, noise_std=0.0,
|
||||
random_images: bool = False):
|
||||
random_images: bool = False, weights=None):
|
||||
model.train()
|
||||
total_loss = 0.0
|
||||
count = 0
|
||||
@@ -127,7 +136,7 @@ def pretrain_one_epoch(model, loader, optimizer, device, image_width,
|
||||
device, random_images)
|
||||
optimizer.zero_grad()
|
||||
pred = model(images, history)
|
||||
loss = torch.nn.functional.mse_loss(pred, target)
|
||||
loss = _weighted_mse(pred, target, weights)
|
||||
loss.backward()
|
||||
if max_grad_norm:
|
||||
torch.nn.utils.clip_grad_norm_(model.parameters(), max_grad_norm)
|
||||
@@ -139,7 +148,7 @@ def pretrain_one_epoch(model, loader, optimizer, device, image_width,
|
||||
|
||||
@torch.no_grad()
|
||||
def validate(model, loader, device, image_width, image_height, frame_len,
|
||||
random_images: bool = False):
|
||||
random_images: bool = False, weights=None):
|
||||
model.eval()
|
||||
total_loss = 0.0
|
||||
count = 0
|
||||
@@ -152,7 +161,7 @@ def validate(model, loader, device, image_width, image_height, frame_len,
|
||||
history.size(0), frame_len, image_height, image_width,
|
||||
device, random_images)
|
||||
pred = model(images, history)
|
||||
loss = torch.nn.functional.mse_loss(pred, target)
|
||||
loss = _weighted_mse(pred, target, weights)
|
||||
total_loss += loss.item() * history.size(0)
|
||||
count += history.size(0)
|
||||
if count == 0:
|
||||
@@ -173,7 +182,6 @@ def main():
|
||||
|
||||
cfg = apply_overrides(Config(), args)
|
||||
validate_config_values(cfg.data, cfg.model, cfg.train)
|
||||
cfg.data.data_dir = args.mt_dir
|
||||
|
||||
os.makedirs(cfg.train.checkpoint_dir, exist_ok=True)
|
||||
|
||||
@@ -205,12 +213,17 @@ def main():
|
||||
train_ds = MTActionDataset(
|
||||
args.mt_dir, cfg.data.history_len, cfg.data.action_dim,
|
||||
file_indices=train_file_indices, files=all_files,
|
||||
normalize_mode=cfg.data.normalize_mode,
|
||||
)
|
||||
|
||||
# 动作归一化（与 train.py 语义一致）：无 stats 文件时按训练集
|
||||
# targets 计算并保存到 checkpoint_dir，验证集复用同一 stats
|
||||
# 动作归一化（与 train.py 语义一致）：zscore 模式无 stats 文件时按训练集
|
||||
# targets 计算并保存到 checkpoint_dir，验证集复用同一 stats；
|
||||
# fixed_range 模式免统计量，跳过此段
|
||||
action_mean = action_std = None
|
||||
if cfg.data.normalize_actions:
|
||||
if cfg.data.normalize_actions and cfg.data.normalize_mode == "fixed_range":
|
||||
# 构造时 action_mean=None 已置 _fixed_range，这里只打印口径
|
||||
print("动作归一化: fixed_range（固定物理范围 min-max→[0,1]，免 stats）")
|
||||
elif cfg.data.normalize_actions:
|
||||
if cfg.data.action_stats_path:
|
||||
if not os.path.exists(cfg.data.action_stats_path):
|
||||
raise FileNotFoundError(
|
||||
@@ -248,6 +261,7 @@ def main():
|
||||
args.mt_dir, cfg.data.history_len, cfg.data.action_dim,
|
||||
file_indices=val_file_indices, files=all_files,
|
||||
action_mean=action_mean, action_std=action_std,
|
||||
normalize_mode=cfg.data.normalize_mode,
|
||||
)
|
||||
|
||||
print(f"Files: {len(train_file_indices)} train, {len(val_file_indices)} val")
|
||||
@@ -272,6 +286,13 @@ def main():
|
||||
model = ActionPredictor(cfg.model, cfg.data, pretrained=False).to(device)
|
||||
n_params = sum(p.numel() for p in model.parameters())
|
||||
print(f"Model params: {n_params:,}")
|
||||
|
||||
# 逐列损失权重（与 train.py 同口径；仅训练损失用）
|
||||
col_w = cfg.data.column_weights
|
||||
if col_w is None:
|
||||
col_w = default_column_weights(cfg.data.action_dim)
|
||||
weights_t = torch.tensor(np.asarray(col_w, dtype=np.float32), device=device)
|
||||
print(f"Column weights: {[round(float(v), 4) for v in weights_t.tolist()]}")
|
||||
print(f"Config: action_dim={cfg.data.action_dim}, "
|
||||
f"history_len={cfg.data.history_len}, "
|
||||
f"frame_len={cfg.data.frame_len}, "
|
||||
@@ -328,34 +349,40 @@ def main():
|
||||
model, train_loader, optimizer, device,
|
||||
cfg.data.image_width, cfg.data.image_height, cfg.data.frame_len,
|
||||
cfg.train.max_grad_norm, args.noise_std, args.random_images,
|
||||
weights=weights_t,
|
||||
)
|
||||
val_loss = validate(model, val_loader, device,
|
||||
cfg.data.image_width, cfg.data.image_height,
|
||||
cfg.data.frame_len, args.random_images)
|
||||
cfg.data.frame_len, args.random_images,
|
||||
weights=weights_t)
|
||||
scheduler.step()
|
||||
print(f" train_loss={train_loss:.6f} val_loss={val_loss:.6f}")
|
||||
|
||||
if val_loss < best_val_loss:
|
||||
best_val_loss = val_loss
|
||||
patience_counter = 0
|
||||
torch.save(
|
||||
{
|
||||
"epoch": epoch,
|
||||
"model_state_dict": model.state_dict(),
|
||||
"optimizer_state_dict": optimizer.state_dict(),
|
||||
"val_loss": val_loss,
|
||||
"config": cfg.to_dict(),
|
||||
},
|
||||
best_path,
|
||||
)
|
||||
torch.save(
|
||||
{
|
||||
"model_state_dict": model.state_dict(),
|
||||
"config": cfg.to_dict(),
|
||||
},
|
||||
inference_path,
|
||||
)
|
||||
print(f" -> saved best (val_loss={val_loss:.6f})")
|
||||
if not np.isfinite(val_loss):
|
||||
print(f"WARNING: val_loss 非有限值（{val_loss}），跳过 best 更新")
|
||||
patience_counter += 1
|
||||
else:
|
||||
best_val_loss = val_loss
|
||||
patience_counter = 0
|
||||
torch.save(
|
||||
{
|
||||
"epoch": epoch,
|
||||
"model_state_dict": model.state_dict(),
|
||||
"optimizer_state_dict": optimizer.state_dict(),
|
||||
"val_loss": val_loss,
|
||||
"config": cfg.to_dict(),
|
||||
},
|
||||
best_path,
|
||||
)
|
||||
torch.save(
|
||||
{
|
||||
"model_state_dict": model.state_dict(),
|
||||
"config": cfg.to_dict(),
|
||||
},
|
||||
inference_path,
|
||||
)
|
||||
print(f" -> saved best (val_loss={val_loss:.6f})")
|
||||
else:
|
||||
patience_counter += 1
|
||||
if patience_counter >= cfg.train.patience:
|
||||
|
||||
Reference in new issue
Block a user