Shaun ZhouandClaude Opus 5
86c86b105c
实际工作流是：simclr 训练 -> 聚类 -> 人工归类 -> 分类训练 -> GradCAM/SHAP 生成
热力图与 box。据此移除不参与其中的检测/定位链路，共 31 个文件、约 2600 行：
- 模型：defect_net、postprocess、necks/、heads/center_head
- 数据：film_defect（YOLO 读取端）、target_encoder
- 引擎：trainer、evaluator、losses
- 入口：train.py、eval.py
- 脚本：convert_annotations、split_dataset、export_onnx、profile_inference
- 配置：configs/{train,eval,model,dataset}
- utils/labels（多类/单类标签模式，仅检测分类头使用）
共享模块按实际用量瘦身：engine/metrics 只留 AverageMeter（检测指标随之移除）；
datasets/yolo 只留写出侧（IMAGE_SUFFIXES 与 write_data_yaml）——第 5 步产出的
YOLO 标签是给外部检测训练用的交换格式，读取端不再需要。
裁剪过程中修掉一个真 bug：generate_boxes 的 --stage 默认 6（layer3）对 tiny_conv
这类非 nn.Sequential 骨架直接抛异常。现在自动退回骨架最终输出并警告，
另加 --stage -1 显式选择最终输出。
五步工作流已端到端实跑验证（simclr 1 轮 -> 聚类 -> 导出 -> 分类 1 轮 ->
gradcam 与 shap 两种方法各生成一遍）。
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
383 lines
16 KiB
Python
383 lines
16 KiB
Python
#!/usr/bin/env python
|
||
"""用训练好的分类模型为每张图生成热力图与 YOLO 框标签。
|
||
|
||
# Grad-CAM（快，全量 11k 张约 2 分钟）
|
||
uv run python scripts/generate_boxes.py --out runs/boxes_gradcam --method gradcam
|
||
|
||
# SHAP Partition（慢但更精细，全量约 1.7 小时）
|
||
uv run python scripts/generate_boxes.py --out runs/boxes_shap --method shap
|
||
|
||
两种归因方法都能定位，取舍不同：
|
||
|
||
| | gradcam | shap |
|
||
| --- | --- | --- |
|
||
| 分辨率 | 受限于特征图（layer3 @128² 只有 8×8） | 与输入同分辨率（128×128） |
|
||
| 单张耗时 | 一次 backward，约 0.01 秒 | 几百次前向，约 0.55 秒 |
|
||
| 小目标 | 几像素的黑点在 8×8 上不可分辨 | 能贴合到几十像素的目标 |
|
||
|
||
产出是一个**自成一体的 YOLO 数据集**，可直接喂给 train.py：
|
||
|
||
```
|
||
runs/<name>/
|
||
├── images/<类别>/<图名>.png # 硬链接到原图，不占额外磁盘
|
||
├── labels/<类别>/<图名>.txt # YOLO：class_id cx cy w h（归一化）
|
||
├── heatmaps/<类别>/<图名>.png # 热力图叠加原图 + 框，供人工核对
|
||
├── data.yaml
|
||
└── summary.json
|
||
```
|
||
|
||
images/ 与 labels/ 的对应关系符合本仓库的 YOLO 约定（datasets/yolo.py），
|
||
所以 `FilmDefectDataset` 能直接读。
|
||
|
||
默认对**全量**数据生成；`--limit` / `--per-class` 只用于快速试参数。
|
||
热力图默认针对模型的 **top1 预测类别**；`--target label` 可改用图片所在目录的标注类别。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import errno
|
||
import json
|
||
import os
|
||
import random
|
||
import shutil
|
||
import sys
|
||
import time
|
||
from collections import Counter
|
||
from pathlib import Path
|
||
|
||
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
||
|
||
import numpy as np # noqa: E402
|
||
import torch # noqa: E402
|
||
from PIL import Image # noqa: E402
|
||
from torch.utils.data import DataLoader # noqa: E402
|
||
|
||
from datasets import FolderClassificationDataset, classification_collate # noqa: E402
|
||
from datasets.yolo import write_data_yaml # noqa: E402
|
||
from engine import load_checkpoint # noqa: E402
|
||
from engine.gradcam import cam_to_boxes, grad_cam, to_yolo_line # noqa: E402
|
||
from models import build_model # noqa: E402
|
||
from utils import load_config, setup_logging # noqa: E402
|
||
from utils.device import DeviceNotAvailableError, describe_device, resolve_device # noqa: E402
|
||
|
||
logger = None
|
||
|
||
METHODS = ("gradcam", "shap")
|
||
|
||
#: 两种方法的归因图分辨率差 16 倍，面积阈值不能共用一个默认值：
|
||
#: 同一个小黑点在 8×8 上占几格、在 128×128 上只占百来像素，
|
||
#: 沿用 0.02（=328 像素）会把它整个滤掉。
|
||
DEFAULT_MIN_AREA_RATIO = {"gradcam": 0.02, "shap": 0.002}
|
||
|
||
|
||
class NameCollision(RuntimeError):
|
||
"""两张不同的源图在产出目录里撞到了同一个文件名。"""
|
||
|
||
|
||
def link_or_copy(source: Path, destination: Path) -> str:
|
||
"""给原图建硬链接；跨文件系统时退回复制。
|
||
|
||
硬链接不占额外磁盘，却表现得和真实文件一样——产出目录可以整个拷走。
|
||
"""
|
||
if destination.exists():
|
||
return "exists"
|
||
destination.parent.mkdir(parents=True, exist_ok=True)
|
||
try:
|
||
os.link(source, destination)
|
||
return "hard"
|
||
except OSError as exc:
|
||
if exc.errno != errno.EXDEV:
|
||
raise
|
||
shutil.copy2(source, destination)
|
||
return "copy"
|
||
|
||
|
||
def save_heatmap(path: Path, image_path: Path, heat: np.ndarray, boxes) -> None:
|
||
"""热力图叠加原图并画框。用 PIL 直接合成而不是 matplotlib：
|
||
全量 11k 张要出图，逐张建 figure 太慢也太占盘。"""
|
||
from matplotlib import colormaps
|
||
|
||
with Image.open(image_path) as raw:
|
||
base = raw.convert("RGB")
|
||
width, height = base.size
|
||
|
||
resized = np.asarray(
|
||
Image.fromarray((heat * 255).astype(np.uint8)).resize((width, height), Image.BILINEAR)
|
||
) / 255.0
|
||
colored = (colormaps["jet"](resized)[..., :3] * 255).astype(np.uint8)
|
||
blended = Image.blend(base, Image.fromarray(colored), alpha=0.45)
|
||
|
||
from PIL import ImageDraw
|
||
|
||
draw = ImageDraw.Draw(blended)
|
||
for x1, y1, x2, y2 in boxes:
|
||
draw.rectangle(
|
||
[x1 * width, y1 * height, x2 * width, y2 * height], outline=(0, 255, 0), width=2
|
||
)
|
||
path.parent.mkdir(parents=True, exist_ok=True)
|
||
blended.save(path)
|
||
|
||
|
||
def parse_args() -> argparse.Namespace:
|
||
parser = argparse.ArgumentParser(
|
||
description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
|
||
)
|
||
parser.add_argument("--out", required=True, help="产出目录，建议放在 runs/ 下")
|
||
parser.add_argument(
|
||
"--method", choices=METHODS, default="gradcam", help="归因方法，默认 gradcam"
|
||
)
|
||
parser.add_argument("--checkpoint", default="runs/classify/best.pth", help="分类模型权重")
|
||
parser.add_argument("--config", default="configs/classify/film.yaml", help="训练时的配置")
|
||
parser.add_argument("--set", nargs="*", default=[], metavar="KEY=VALUE")
|
||
parser.add_argument("--device", default=None)
|
||
parser.add_argument(
|
||
"--target", choices=("predicted", "label"), default="predicted",
|
||
help="热力图针对哪个类别：predicted=模型 top1 预测（默认），label=图片所在目录",
|
||
)
|
||
|
||
parser.add_argument("--threshold", type=float, default=0.4, help="热力图阈值（相对最大值）")
|
||
parser.add_argument(
|
||
"--max-boxes", type=int, default=1,
|
||
help="每张图最多保留几个框，按归因总量排序取前 N 个。"
|
||
"默认 1：一张裁片通常只对应一处缺陷",
|
||
)
|
||
parser.add_argument("--padding", type=float, default=0.1, help="框四周外扩比例")
|
||
parser.add_argument(
|
||
"--min-area-ratio", type=float, default=None,
|
||
help=f"连通域面积下限（占整图比例）。缺省随方法而定：{DEFAULT_MIN_AREA_RATIO}",
|
||
)
|
||
parser.add_argument(
|
||
"--peak-ratio", type=float, default=0.75,
|
||
help="次要连通域的峰值需达到全局最大值的这个比例才保留，用于滤掉弱响应假框",
|
||
)
|
||
|
||
parser.add_argument(
|
||
"--stage", type=int, default=6,
|
||
help="gradcam 的目标层（torchvision 骨架：4~7 = layer1~4）。默认 6 即 layer3（8×8）；"
|
||
"layer4 只有 4×4 太粗，layer2 响应太散。-1 表示用骨架最终输出——"
|
||
"tiny_conv 这类不是 nn.Sequential 的骨架只能这样取",
|
||
)
|
||
parser.add_argument("--max-evals", type=int, default=500, help="shap 每张图的前向次数")
|
||
parser.add_argument("--smooth-radius", type=int, default=2, help="shap 归因图平滑半径，0=不平滑")
|
||
|
||
parser.add_argument("--no-heatmaps", action="store_true", help="不输出热力图，只出标签")
|
||
parser.add_argument("--no-images", action="store_true", help="不建原图硬链接")
|
||
parser.add_argument("--limit", type=int, default=0, help="只处理前 N 张（试参数用）")
|
||
parser.add_argument(
|
||
"--per-class", type=int, default=0, help="每类只处理 N 张（试参数用），0=全量"
|
||
)
|
||
parser.add_argument("--seed", type=int, default=0, help="--per-class 抽样的随机种子")
|
||
return parser.parse_args()
|
||
|
||
|
||
def main() -> int:
|
||
global logger
|
||
args = parse_args()
|
||
out_dir = Path(args.out)
|
||
out_dir.mkdir(parents=True, exist_ok=True)
|
||
logger = setup_logging(out_dir / "generate_boxes.log")
|
||
|
||
cfg = load_config(args.config, args.set)
|
||
try:
|
||
device = resolve_device(args.device or cfg.get("device", "auto"))
|
||
except DeviceNotAvailableError as exc:
|
||
logger.error("%s", exc)
|
||
return 1
|
||
|
||
data_cfg = cfg["data"]
|
||
dataset = FolderClassificationDataset(
|
||
root=data_cfg["root"], split="all", classes=data_cfg.get("classes"),
|
||
transforms=data_cfg["val_transforms"], exclude=data_cfg.get("exclude") or [],
|
||
)
|
||
classes = dataset.classes
|
||
|
||
if args.per_class:
|
||
grouped: dict[int, list] = {}
|
||
for sample in dataset.samples:
|
||
grouped.setdefault(sample[1], []).append(sample)
|
||
rng = random.Random(args.seed)
|
||
dataset.samples = [
|
||
s for group in grouped.values() for s in rng.sample(group, min(args.per_class, len(group)))
|
||
]
|
||
if args.limit:
|
||
dataset.samples = dataset.samples[: args.limit]
|
||
|
||
model_cfg = dict(cfg["model"])
|
||
model_cfg.setdefault("num_classes", len(classes))
|
||
model_cfg["init_from"] = None # 权重来自 checkpoint
|
||
model = build_model(model_cfg)
|
||
load_checkpoint(args.checkpoint, model, map_location=device)
|
||
model.to(device).eval()
|
||
for param in model.parameters(): # 归因需要梯度，但不更新权重
|
||
param.requires_grad_(True)
|
||
|
||
stage = args.stage if args.stage >= 0 else None
|
||
if stage is not None and not isinstance(
|
||
getattr(model.backbone, "features", None), torch.nn.Sequential
|
||
):
|
||
# tiny_conv 这类骨架没有 nn.Sequential 的 features，取不了中间层；
|
||
# 退回最终输出而不是直接崩掉
|
||
logger.warning(
|
||
"骨架 %s 不是 nn.Sequential，无法按 stage 取中间层，改用最终输出"
|
||
"（分辨率更低，如需更精细请换 torchvision 骨架）",
|
||
type(model.backbone).__name__,
|
||
)
|
||
stage = None
|
||
|
||
min_area_ratio = (
|
||
args.min_area_ratio if args.min_area_ratio is not None
|
||
else DEFAULT_MIN_AREA_RATIO[args.method]
|
||
)
|
||
box_kwargs = {
|
||
"threshold": args.threshold, "min_area_ratio": min_area_ratio,
|
||
"max_boxes": args.max_boxes, "padding": args.padding, "peak_ratio": args.peak_ratio,
|
||
}
|
||
|
||
logger.info("设备: %s | 权重: %s", describe_device(device), args.checkpoint)
|
||
logger.info("方法: %s | 目标类别: %s", args.method, args.target)
|
||
logger.info("数据集 %s：%d 张，%d 类", data_cfg["root"], len(dataset), len(classes))
|
||
logger.info("框参数: %s", box_kwargs)
|
||
if args.method == "shap":
|
||
logger.warning(
|
||
"shap 单张约 0.55 秒，%d 张预计 %.1f 分钟；只想试参数可用 --per-class / --limit",
|
||
len(dataset), len(dataset) * 0.55 / 60,
|
||
)
|
||
|
||
started = time.time()
|
||
box_counts: Counter[int] = Counter()
|
||
link_modes: Counter[str] = Counter()
|
||
seen: dict[Path, Path] = {}
|
||
agree = 0
|
||
heat_shape = None
|
||
|
||
if args.method == "gradcam":
|
||
loader = DataLoader(
|
||
dataset,
|
||
batch_size=int(data_cfg.get("loader", {}).get("batch_size", 64)),
|
||
shuffle=False,
|
||
num_workers=int(data_cfg.get("loader", {}).get("num_workers", 4)),
|
||
collate_fn=classification_collate,
|
||
)
|
||
processed = 0
|
||
for step, batch in enumerate(loader):
|
||
images = batch["images"].to(device)
|
||
labels = batch["labels"].to(device)
|
||
with torch.no_grad():
|
||
predicted = model(images).argmax(1)
|
||
targets = predicted if args.target == "predicted" else labels
|
||
agree += int((predicted == labels).sum())
|
||
heats = grad_cam(model.backbone, model.head, images, targets, stage=stage)
|
||
heat_shape = tuple(heats.shape[-2:])
|
||
|
||
for heat, target, meta in zip(
|
||
heats.cpu().numpy(), targets.cpu().tolist(), batch["meta"], strict=True
|
||
):
|
||
try:
|
||
_emit(out_dir, Path(meta["path"]), classes, target, heat, box_kwargs,
|
||
args, box_counts, link_modes, seen)
|
||
except NameCollision as exc:
|
||
logger.error("%s", exc)
|
||
return 1
|
||
processed += 1
|
||
if step % 20 == 0:
|
||
logger.info("处理 [%d/%d]", processed, len(dataset))
|
||
else:
|
||
from engine.shap_explain import shap_attribution, smooth
|
||
|
||
for index in range(len(dataset)):
|
||
sample = dataset[index]
|
||
image_chw = sample["image"]
|
||
with torch.no_grad():
|
||
predicted = int(model(image_chw[None].to(device)).argmax(1))
|
||
agree += int(predicted == sample["label"])
|
||
target = predicted if args.target == "predicted" else sample["label"]
|
||
|
||
heat = shap_attribution(
|
||
model, image_chw.permute(1, 2, 0).numpy().astype(np.float32), target, device,
|
||
max_evals=args.max_evals,
|
||
)
|
||
heat = smooth(heat, args.smooth_radius)
|
||
heat_shape = heat.shape
|
||
try:
|
||
_emit(out_dir, Path(sample["meta"]["path"]), classes, target, heat, box_kwargs,
|
||
args, box_counts, link_modes, seen)
|
||
except NameCollision as exc:
|
||
logger.error("%s", exc)
|
||
return 1
|
||
if index % 50 == 0:
|
||
elapsed = time.time() - started
|
||
logger.info(
|
||
"处理 [%d/%d] 已用 %.0fs，平均 %.2fs/张", index, len(dataset),
|
||
elapsed, elapsed / max(index, 1),
|
||
)
|
||
|
||
total = sum(box_counts.values())
|
||
write_data_yaml(out_dir / "data.yaml", classes, root=out_dir,
|
||
train="images", val="images")
|
||
summary = {
|
||
"method": args.method,
|
||
"checkpoint": args.checkpoint,
|
||
"dataset": str(data_cfg["root"]),
|
||
"target": args.target,
|
||
"num_images": total,
|
||
"heatmap_shape": list(heat_shape) if heat_shape else None,
|
||
"seconds_per_image": (time.time() - started) / max(total, 1),
|
||
"box_params": box_kwargs,
|
||
"stage": stage if args.method == "gradcam" else None,
|
||
"max_evals": args.max_evals if args.method == "shap" else None,
|
||
"prediction_matches_folder_label": agree / total if total else 0.0,
|
||
"boxes_per_image": {str(k): v for k, v in sorted(box_counts.items())},
|
||
"link_modes": dict(link_modes),
|
||
}
|
||
(out_dir / "summary.json").write_text(
|
||
json.dumps(summary, ensure_ascii=False, indent=2), encoding="utf-8"
|
||
)
|
||
|
||
logger.info(
|
||
"完成 %d 张，热力图 %s，平均 %.3fs/张", total, heat_shape, summary["seconds_per_image"]
|
||
)
|
||
logger.info("模型预测与目录标注一致率: %.4f", summary["prediction_matches_folder_label"])
|
||
for count, number in sorted(box_counts.items()):
|
||
logger.info(" 生成 %d 个框: %d 张 (%.1f%%)", count, number, 100 * number / total)
|
||
if link_modes:
|
||
logger.info("原图链接方式: %s", dict(link_modes))
|
||
logger.info("产出目录: %s", out_dir)
|
||
return 0
|
||
|
||
|
||
def _emit(out_dir, source, classes, target, heat, box_kwargs, args, box_counts, link_modes,
|
||
seen) -> None:
|
||
"""把一张图的结果落盘：硬链接 + YOLO 标签 + 热力图。
|
||
|
||
产出按**预测类别**分目录，而源图来自不同的类别目录，所以两张同名的源图
|
||
（dirA/0.png 与 dirB/0.png）可能落到同一个目标路径上——后写的会覆盖前一个的标签。
|
||
这里显式挡住，而不是让标签悄悄丢失。
|
||
"""
|
||
name = classes[target]
|
||
boxes = cam_to_boxes(heat, **box_kwargs)
|
||
box_counts[len(boxes)] += 1
|
||
|
||
label_path = out_dir / "labels" / name / f"{source.stem}.txt"
|
||
previous = seen.get(label_path)
|
||
if previous is not None:
|
||
raise NameCollision(
|
||
f"{previous} 与 {source} 在产出目录里都要写 {label_path}，后者会覆盖前者。"
|
||
"源图文件名需要全局唯一——用 scripts/export_clusters.py --prefix-parent "
|
||
"重新导出数据集即可。"
|
||
)
|
||
seen[label_path] = source
|
||
label_path.parent.mkdir(parents=True, exist_ok=True)
|
||
label_path.write_text(
|
||
"\n".join(to_yolo_line(box, target) for box in boxes) + ("\n" if boxes else ""),
|
||
encoding="utf-8",
|
||
)
|
||
if not args.no_images:
|
||
link_modes[link_or_copy(source, out_dir / "images" / name / source.name)] += 1
|
||
if not args.no_heatmaps:
|
||
save_heatmap(out_dir / "heatmaps" / name / f"{source.stem}.png", source, heat, boxes)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
raise SystemExit(main())
|