From ea1fc21dc4099c2b5430e5324ed19c04f48adfd4 Mon Sep 17 00:00:00 2001
From: zhangpu <1250681871@qq.com>
Date: Tue, 7 Apr 2026 16:23:21 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E6=94=B9=E9=85=8D=E7=BD=AE=E6=96=87?=
 =?UTF-8?q?=E4=BB=B6?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 data_management/count_images.py | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/data_management/count_images.py b/data_management/count_images.py
index 4fb343f..9d83a2c 100644
--- a/data_management/count_images.py
+++ b/data_management/count_images.py
@@ -149,6 +149,17 @@ def export_to_excel(sorted_classes, class_counts_detail, class_counts,
     note_cell.border    = make_border()
     ws.row_dimensions[last_row].height = 22
 
+    # ── 备注行：采样目标说明 ─────────────────────────────────────
+    remark_row = last_row + 1
+    ws.merge_cells(f"A{remark_row}:F{remark_row}")
+    remark_cell = ws[f"A{remark_row}"]
+    remark_cell.value = "现阶段目标：每个类别至少 100 张样本。后期可根据实际情况调整阈值。高质量样本越多，模型泛化能力越强。"
+    remark_cell.font      = make_font(color="64748B", size=9)
+    remark_cell.alignment = center
+    remark_cell.fill      = make_fill("EFF6FF")
+    remark_cell.border    = make_border()
+    ws.row_dimensions[remark_row].height = 18
+
     # ── 列宽自适应 ───────────────────────────────────────────────
     col_widths = [40, 8, 8, 8, 8, 12]
     for col_idx, width in enumerate(col_widths, start=1):
@@ -239,7 +250,7 @@ def count_images_by_class(dataset_root: str, output_file: str = None,
 
     # 按数量降序排列
     sorted_classes = sorted(class_counts.items(), key=lambda x: x[1], reverse=True)
-    min_threshold  = 10
+    min_threshold  = 100
     insufficient_count = 0
 
     # ── 控制台输出 ──────────────────────────────────────────────