feat(detect): 全量推理可视化，预测框与真值框画在一起

scripts/visualize_detections.py：在整个数据集上推理，绿=真值、蓝=命中的预测、
红=没对上真值的预测，按结果类型分目录（ok / missed / extra / none），再配一份
index.csv（逐图的真值数、预测数、命中数、最高置信度）与 summary.json（逐类 TP/FP/FN）。
--only errors 只输出有问题的图。

匹配逻辑放在 engine/detection.py：按置信度贪心、IoU 阈值、类别需一致，与 mAP 的规则
一致，所以图上看到的漏检误检和指标算的是同一回事。same_class=False 可以单看定位准不准
——定位对但分类错，和完全没找到是两种问题。

train 与 val 分开放：训练集的图模型见过，那部分结果不能当泛化能力看。

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

tests/test_detection.py

@@ -0,0 +1,131 @@
+"""检测结果的匹配与绘制。"""
+
+import pytest
+
+pytest.importorskip("PIL")
+
+from engine.detection import (  # noqa: E402
+    COLOR_GT,
+    COLOR_MATCHED,
+    COLOR_UNMATCHED,
+    Box,
+    draw_boxes,
+    from_yolo,
+    iou,
+    match_boxes,
+    parse_label,
+)
+
+
+def test_from_yolo_converts_center_to_corners():
+    assert from_yolo(2, 0.5, 0.5, 0.2, 0.4) == Box(2, 0.4, 0.3, 0.6, 0.7)
+
+
+def test_parse_label_reads_boxes_and_empty_files():
+    boxes = parse_label("0 0.5 0.5 0.2 0.2\n3 0.1 0.1 0.1 0.1\n")
+    assert [b.class_id for b in boxes] == [0, 3]
+    assert parse_label("") == []          # 负样本
+    assert parse_label("\n\n") == []
+
+
+@pytest.mark.parametrize(
+    "a,b,expected",
+    [
+        ((0, 0, 1, 1), (0, 0, 1, 1), 1.0),          # 完全重合
+        ((0, 0, 1, 1), (2, 2, 3, 3), 0.0),          # 不相交
+        ((0, 0, 1, 1), (1, 1, 2, 2), 0.0),          # 只碰到角
+        ((0, 0, 2, 2), (1, 1, 3, 3), 1 / 7),        # 交 1，并 7
+    ],
+)
+def test_iou(a, b, expected):
+    assert iou(Box(0, *a), Box(0, *b)) == pytest.approx(expected)
+
+
+def test_matches_by_confidence_first():
+    """两个预测抢同一个真值时，置信度高的赢——与 mAP 的规则一致。"""
+    truth = [from_yolo(0, 0.5, 0.5, 0.2, 0.2)]
+    weak = Box(0, 0.4, 0.4, 0.6, 0.6, 0.3)
+    strong = Box(0, 0.41, 0.41, 0.59, 0.59, 0.9)
+    match = match_boxes([weak, strong], truth, iou_threshold=0.3)
+
+    assert match.pairs == [(1, 0)]                  # 下标 1 = strong
+    assert match.unmatched_predictions == [0]
+    assert match.unmatched_ground_truth == []
+
+
+def test_low_iou_counts_as_both_miss_and_false_positive():
+    truth = [from_yolo(0, 0.2, 0.2, 0.1, 0.1)]
+    prediction = Box(0, 0.7, 0.7, 0.9, 0.9, 0.9)
+    match = match_boxes([prediction], truth)
+    assert match.pairs == []
+    assert match.unmatched_predictions == [0]       # 误检
+    assert match.unmatched_ground_truth == [0]      # 同时也是漏检
+
+
+def test_class_mismatch_is_not_a_hit_unless_allowed():
+    """定位准但分类错：默认不算命中，same_class=False 时可单看位置。"""
+    truth = [from_yolo(1, 0.5, 0.5, 0.2, 0.2)]
+    prediction = Box(0, 0.4, 0.4, 0.6, 0.6, 0.9)
+
+    assert match_boxes([prediction], truth).pairs == []
+    assert match_boxes([prediction], truth, same_class=False).pairs == [(0, 0)]
+
+
+def test_each_ground_truth_is_claimed_once():
+    """一个真值只能被一个预测认领，多出来的预测算误检。"""
+    truth = [from_yolo(0, 0.5, 0.5, 0.4, 0.4)]
+    predictions = [
+        Box(0, 0.31, 0.31, 0.69, 0.69, 0.9),
+        Box(0, 0.32, 0.32, 0.68, 0.68, 0.8),
+    ]
+    match = match_boxes(predictions, truth)
+    assert len(match.pairs) == 1
+    assert len(match.unmatched_predictions) == 1
+
+
+def test_no_prediction_on_background_is_clean():
+    match = match_boxes([], [])
+    assert match == ([], [], [])
+
+
+def test_multiple_boxes_are_matched_pairwise():
+    truth = [from_yolo(0, 0.2, 0.2, 0.1, 0.1), from_yolo(1, 0.8, 0.8, 0.1, 0.1)]
+    predictions = [
+        Box(1, 0.75, 0.75, 0.85, 0.85, 0.7),
+        Box(0, 0.15, 0.15, 0.25, 0.25, 0.9),
+    ]
+    match = match_boxes(predictions, truth)
+    assert sorted(match.pairs) == [(0, 1), (1, 0)]
+    assert not match.unmatched_predictions and not match.unmatched_ground_truth
+
+
+def _colors(image):
+    return {pixel for pixel in image.getdata()}
+
+
+def test_draw_uses_a_distinct_colour_per_role():
+    """三种角色三种颜色：绿=真值，蓝=命中的预测，红=没对上的预测。"""
+    from PIL import Image
+
+    truth = [from_yolo(0, 0.25, 0.25, 0.2, 0.2), from_yolo(0, 0.75, 0.25, 0.2, 0.2)]
+    predictions = [
+        Box(0, 0.16, 0.16, 0.34, 0.34, 0.9),      # 命中第一个
+        Box(0, 0.5, 0.8, 0.6, 0.9, 0.4),          # 没有对应真值
+    ]
+    match = match_boxes(predictions, truth, iou_threshold=0.5)
+    assert match.pairs == [(0, 0)]
+
+    image = Image.new("RGB", (200, 200), "black")
+    draw_boxes(image, truth, predictions, ["blackdot"], match)
+    present = _colors(image)
+    assert COLOR_GT in present and COLOR_MATCHED in present and COLOR_UNMATCHED in present
+
+
+def test_draw_handles_boxes_at_the_border():
+    """框贴着上边缘时，标签文字要画到框内，不能画到图外去。"""
+    from PIL import Image
+
+    image = Image.new("RGB", (64, 64), "black")
+    prediction = Box(0, 0.0, 0.0, 0.5, 0.05, 0.9)
+    draw_boxes(image, [], [prediction], ["blackdot"], match_boxes([prediction], []))
+    assert COLOR_UNMATCHED in _colors(image)