bushu

zhuangtai_class_cls/chose_ROI.py

@@ -75,7 +75,7 @@ def select_roi(image_path):
         if key == ord('s'):
             # 保存坐标
             base_name = os.path.splitext(os.path.basename(image_path))[0]
-            save_path = os.path.join(save_dir, f"{base_name}_rois.txt")  # 修改了扩展名为 .txt
+            save_path = os.path.join(save_dir, f"{base_name}_rois1.txt")  # 修改了扩展名为 .txt
             save_rois_to_txt(roi_list, save_path)  # 使用新的保存函数
 
         elif key == ord('n'):

zhuangtai_class_cls/resize_dataset.py

@@ -1,84 +0,0 @@
-import cv2
-import os
-
-# 配置路径
-original_images_parent_dir = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/classdata3/val"  # 含 class0, class1 等
-roi_coords_file = "./roi_coordinates/1_rois.txt"  # 你手动标注的唯一一个 ROI 文件
-output_parent_dir = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/classdata3/classdata3_cropped"
-target_size = 640
-
-os.makedirs(output_parent_dir, exist_ok=True)
-
-def load_global_rois(txt_path):
-    """加载全局 ROI 坐标"""
-    rois = []
-    if not os.path.exists(txt_path):
-        print(f"❌ ROI 文件不存在: {txt_path}")
-        return rois
-    with open(txt_path, 'r') as f:
-        for line in f:
-            line = line.strip()
-            if line:
-                try:
-                    x, y, w, h = map(int, line.split(','))
-                    rois.append((x, y, w, h))
-                    print(f"📌 加载 ROI: (x={x}, y={y}, w={w}, h={h})")
-                except Exception as e:
-                    print(f"⚠️ 无法解析 ROI 行: {line}, 错误: {e}")
-    return rois
-
-# 加载全局 ROI
-rois = load_global_rois(roi_coords_file)
-if len(rois) == 0:
-    print("❌ 没有加载到任何有效的 ROI 坐标，程序退出。")
-    exit(1)
-
-# 遍历所有子目录和图像
-for class_name in os.listdir(original_images_parent_dir):
-    class_dir = os.path.join(original_images_parent_dir, class_name)
-    if not os.path.isdir(class_dir):
-        continue
-
-    # 创建输出类别目录
-    output_class_dir = os.path.join(output_parent_dir, class_name)
-    os.makedirs(output_class_dir, exist_ok=True)
-
-    print(f"🔄 处理类别: {class_name}")
-
-    for img_file in os.listdir(class_dir):
-        if not img_file.lower().endswith(('.jpg', '.jpeg', '.png', '.bmp')):
-            continue
-
-        img_path = os.path.join(class_dir, img_file)
-        base_name, ext = os.path.splitext(img_file)
-
-        # 读取图像
-        img = cv2.imread(img_path)
-        if img is None:
-            print(f"❌ 无法读取图像: {img_path}")
-            continue
-
-        # 对每一个 ROI 进行裁剪
-        for i, (x, y, w, h) in enumerate(rois):
-            # 检查坐标是否越界
-            h_img, w_img = img.shape[:2]
-            if x < 0 or y < 0 or x + w > w_img or y + h > h_img:
-                print(f"⚠️ ROI 越界，跳过: {x},{y},{w},{h} in {img_path}")
-                continue
-
-            roi_img = img[y:y+h, x:x+w]
-            if roi_img.size == 0:
-                print(f"⚠️ 空 ROI 区域: {x},{y},{w},{h} in {img_path}")
-                continue
-
-            # resize
-            roi_resized = cv2.resize(roi_img, (target_size, target_size), interpolation=cv2.INTER_AREA)
-
-            # 保存文件名：原名 + _roi0, _roi1...
-            suffix = f"_roi{i}" if len(rois) > 1 else ""
-            save_filename = f"{base_name}{suffix}{ext}"
-            save_path = os.path.join(output_class_dir, save_filename)
-            cv2.imwrite(save_path, roi_resized)
-            print(f"✅ 保存: {save_path}")
-
-print("🎉 所有图像已根据全局 ROI 裁剪并保存完成！")

zhuangtai_class_cls/resize_dataset_image.py

@@ -0,0 +1,58 @@
+import os
+import cv2
+
+# ----------------------------
+# 配置
+# ----------------------------
+SOURCE_ROOT_DIR = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/classdata2"       # 原始图片根目录
+TARGET_ROOT_DIR = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/classdata4"    # 输出根目录
+CLASSES = ["class0", "class1", "class2", "class3", "class4"]  # 类别列表
+TARGET_SIZE = 640           # resize 尺寸
+SUBSETS = ["train", "val", "test"]
+
+# ----------------------------
+# 全局 ROI (x, y, w, h)
+# ----------------------------
+GLOBAL_ROI = [859,810,696,328]
+
+# ----------------------------
+# 主处理函数
+# ----------------------------
+def process_images():
+    x, y, w, h = GLOBAL_ROI
+    for subset in SUBSETS:
+        for class_dir in CLASSES:
+            src_dir = os.path.join(SOURCE_ROOT_DIR, subset, class_dir)
+            tgt_dir = os.path.join(TARGET_ROOT_DIR, subset, class_dir)
+            os.makedirs(tgt_dir, exist_ok=True)
+
+            if not os.path.exists(src_dir):
+                print(f"警告: 源目录 {src_dir} 不存在，跳过")
+                continue
+
+            for file in os.listdir(src_dir):
+                if not (file.endswith(".jpg") or file.endswith(".png")):
+                    continue
+
+                img_path = os.path.join(src_dir, file)
+                img = cv2.imread(img_path)
+                if img is None:
+                    print(f"❌ 无法读取图片: {img_path}")
+                    continue
+
+                h_img, w_img = img.shape[:2]
+                x1, y1 = max(0, x), max(0, y)
+                x2, y2 = min(w_img, x + w), min(h_img, y + h)
+
+                cropped = img[y1:y2, x1:x2]
+                if cropped.size == 0:
+                    print(f"❌ 裁剪结果为空: {file}")
+                    continue
+
+                resized = cv2.resize(cropped, (TARGET_SIZE, TARGET_SIZE))
+                tgt_path = os.path.join(tgt_dir, file)
+                cv2.imwrite(tgt_path, resized)
+                print(f"✅ 图片处理完成: {subset}/{class_dir}/{file}")
+
+if __name__ == "__main__":
+    process_images()

zhuangtai_class_cls/resize_main.py

@@ -97,9 +97,9 @@ def classify_and_save_images(model_path, input_folder, output_root, roi_file, ta
 # 主程序
 # ---------------------------
 if __name__ == "__main__":
-    model_path = "/home/hx/yolo/ultralytics_yolo11-main/runs/train/cls_resize/exp_cls2/weights/best.pt"
+    model_path = r"best.pt"
     input_folder = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/f6"
-    output_root = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/class111"
+    output_root = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/class44"
     roi_file = "./roi_coordinates/1_rois.txt"  # 训练时使用的 ROI 文件
     target_size = 640
 

zhuangtai_class_cls/resize_tuili_file.py

@@ -134,8 +134,8 @@ def batch_classify_images(model_path, input_folder, output_root, roi_file, targe
 # ---------------------------
 if __name__ == "__main__":
     model_path = "/home/hx/yolo/ultralytics_yolo11-main/runs/train/cls_resize/exp_cls2/weights/best.pt"
-    input_folder = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/f6"
-    output_root = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/classified"
+    input_folder = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/1000"
+    output_root = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/1000/classified"
     roi_file = "./roi_coordinates/1_rois.txt"
     target_size = 640
     threshold = 0.4  # 可调节的比例系数

zhuangtai_class_cls/resize_tuili_image_main.py

@@ -0,0 +1,168 @@
+import os
+from pathlib import Path
+import cv2
+import numpy as np
+from ultralytics import YOLO
+
+# ---------------------------
+# 类别映射
+# ---------------------------
+CLASS_NAMES = {
+    0: "未堆料",
+    1: "小堆料",
+    2: "大堆料",
+    3: "未浇筑满",
+    4: "浇筑满"
+}
+
+# ---------------------------
+# 加载 ROI 列表
+# ---------------------------
+def load_global_rois(txt_path):
+    rois = []
+    if not os.path.exists(txt_path):
+        print(f"❌ ROI 文件不存在: {txt_path}")
+        return rois
+    with open(txt_path, 'r') as f:
+        for line in f:
+            s = line.strip()
+            if s:
+                try:
+                    x, y, w, h = map(int, s.split(','))
+                    rois.append((x, y, w, h))
+                except Exception as e:
+                    print(f"无法解析 ROI 行 '{s}': {e}")
+    return rois
+
+# ---------------------------
+# 裁剪并 resize ROI
+# ---------------------------
+def crop_and_resize(img, rois, target_size=640):
+    crops = []
+    h_img, w_img = img.shape[:2]
+    for i, (x, y, w, h) in enumerate(rois):
+        if x < 0 or y < 0 or x + w > w_img or y + h > h_img:
+            continue
+        roi = img[y:y+h, x:x+w]
+        roi_resized = cv2.resize(roi, (target_size, target_size), interpolation=cv2.INTER_AREA)
+        crops.append((roi_resized, i))
+    return crops
+
+# ---------------------------
+# class1/class2 加权判断
+# ---------------------------
+def weighted_small_large(pred_probs, threshold=0.4, w1=0.3, w2=0.7):
+    p1 = float(pred_probs[1])
+    p2 = float(pred_probs[2])
+    total = p1 + p2
+    if total > 0:
+        score = (w1 * p1 + w2 * p2) / total
+    else:
+        score = 0.0
+    final_class = "大堆料" if score >= threshold else "小堆料"
+    return final_class, score, p1, p2
+
+# ---------------------------
+# 单张图片推理函数
+# ---------------------------
+def classify_image_weighted(image, model, threshold=0.4):
+    results = model(image)
+    pred_probs = results[0].probs.data.cpu().numpy().flatten()
+    class_id = int(pred_probs.argmax())
+    confidence = float(pred_probs[class_id])
+    class_name = CLASS_NAMES.get(class_id, f"未知类别({class_id})")
+
+    # class1/class2 使用加权得分
+    if class_id in [1, 2]:
+        final_class, score, p1, p2 = weighted_small_large(pred_probs, threshold=threshold)
+    else:
+        final_class = class_name
+        score = confidence
+        p1 = float(pred_probs[1])
+        p2 = float(pred_probs[2])
+
+    return final_class, score, p1, p2
+
+# ---------------------------
+# 批量推理主函数
+# ---------------------------
+def batch_classify_images(model_path, input_folder, output_root, roi_file, target_size=640, threshold=0.5):
+    # 加载模型
+    model = YOLO(model_path)
+
+    # 确保输出根目录存在
+    output_root = Path(output_root)
+    output_root.mkdir(parents=True, exist_ok=True)
+
+    # 为所有类别创建目录
+    class_dirs = {}
+    for name in CLASS_NAMES.values():
+        d = output_root / name
+        d.mkdir(exist_ok=True)
+        class_dirs[name] = d
+
+    rois = load_global_rois(roi_file)
+    if not rois:
+        print("❌ 没有有效 ROI，退出")
+        return
+
+    # 遍历图片
+    for img_path in Path(input_folder).glob("*.*"):
+        if img_path.suffix.lower() not in ['.jpg', '.jpeg', '.png', '.bmp', '.tif']:
+            continue
+        try:
+            img = cv2.imread(str(img_path))
+            if img is None:
+                continue
+
+            crops = crop_and_resize(img, rois, target_size)
+
+            for roi_resized, roi_idx in crops:
+                final_class, score, p1, p2 = classify_image_weighted(roi_resized, model, threshold=threshold)
+
+                # 文件名中保存 ROI、类别、加权分数、class1/class2 置信度
+                suffix = f"_roi{roi_idx}_{final_class}_score{score:.2f}_p1{p1:.2f}_p2{p2:.2f}"
+                dst_path = class_dirs[final_class] / f"{img_path.stem}{suffix}{img_path.suffix}"
+                cv2.imwrite(dst_path, roi_resized)
+                print(f"{img_path.name}{suffix} -> {final_class} (score={score:.2f}, p1={p1:.2f}, p2={p2:.2f})")
+
+        except Exception as e:
+            print(f"处理失败 {img_path.name}: {e}")
+
+
+# ---------------------------
+# 单张图片使用示例（保留 ROI，不保存文件）
+# ---------------------------
+if __name__ == "__main__":
+    model_path = r"best.pt"
+    image_path = r"./test_image/1.jpg"  # 单张图片路径
+    roi_file = r"./roi_coordinates/1_rois.txt"
+    target_size = 640
+    threshold = 0.4  #加权得分阈值可以根据大小堆料分类结果进行调整
+
+    # 加载模型
+    model = YOLO(model_path)
+
+    # 读取 ROI
+    rois = load_global_rois(roi_file)
+    if not rois:
+        print("❌ 没有有效 ROI，退出")
+        exit(1)
+
+    # 读取图片
+    img = cv2.imread(image_path)
+    if img is None:
+        print(f"❌ 无法读取图片: {image_path}")
+        exit(1)
+
+    # 注意：必须裁剪 ROI 并推理，因为训练的时候输入的图像是经过resize的
+    crops = crop_and_resize(img, rois, target_size)
+    for roi_resized, roi_idx in crops:
+        #final_class, score, p1, p2 = classify_image_weighted(roi_resized, model, threshold=threshold)
+        final_class,_,_,_ = classify_image_weighted(roi_resized, model, threshold=threshold)
+        # 只输出信息，不保存文件
+        #print(f"ROI {roi_idx} -> 类别: {final_class}, 加权分数: {score:.2f}, "
+              #f"class1 置信度: {p1:.2f}, class2 置信度: {p2:.2f}")
+        print(f"类别: {final_class}")
+
+

zhuangtai_class_cls/roi_coordinates/1_rois1.txt

@@ -0,0 +1 @@
+626,725,1247,509

zhuangtai_class_cls/tuili_f_yuantusave.py

@@ -0,0 +1,198 @@
+import os
+from pathlib import Path
+import cv2
+import numpy as np
+from ultralytics import YOLO
+
+# ---------------------------
+# 类别映射
+# ---------------------------
+CLASS_NAMES = {
+    0: "未堆料",
+    1: "小堆料",
+    2: "大堆料",
+    3: "未浇筑满",
+    4: "浇筑满"
+}
+
+# ---------------------------
+# 加载 ROI 列表
+# ---------------------------
+def load_global_rois(txt_path):
+    rois = []
+    if not os.path.exists(txt_path):
+        print(f"❌ ROI 文件不存在: {txt_path}")
+        return rois
+    with open(txt_path, 'r') as f:
+        for line in f:
+            s = line.strip()
+            if s:
+                try:
+                    x, y, w, h = map(int, s.split(','))
+                    rois.append((x, y, w, h))
+                except Exception as e:
+                    print(f"⚠️ 无法解析 ROI 行 '{s}': {e}")
+    return rois
+
+
+# ---------------------------
+# 裁剪并 resize ROI
+# ---------------------------
+def crop_and_resize(img, rois, target_size=640):
+    crops = []
+    h_img, w_img = img.shape[:2]
+    for i, (x, y, w, h) in enumerate(rois):
+        # 边界检查
+        if x < 0 or y < 0 or x + w > w_img or y + h > h_img:
+            print(f"⚠️ ROI 超出图像边界，跳过: ({x}, {y}, {w}, {h})")
+            continue
+        roi = img[y:y+h, x:x+w]
+        roi_resized = cv2.resize(roi, (target_size, target_size), interpolation=cv2.INTER_AREA)
+        crops.append((roi_resized, i))
+    return crops
+
+
+# ---------------------------
+# class1/class2 加权判断
+# ---------------------------
+def weighted_small_large(pred_probs, threshold=0.4, w1=0.3, w2=0.7):
+    p1 = float(pred_probs[1])
+    p2 = float(pred_probs[2])
+    total = p1 + p2
+    if total > 0:
+        score = (w1 * p1 + w2 * p2) / total
+    else:
+        score = 0.0
+    final_class = "大堆料" if score >= threshold else "小堆料"
+    return final_class, score, p1, p2
+
+
+# ---------------------------
+# 单张图片推理函数
+# ---------------------------
+def classify_image_weighted(image, model, threshold=0.5):
+    results = model(image)
+    pred_probs = results[0].probs.data.cpu().numpy().flatten()
+    class_id = int(pred_probs.argmax())
+    confidence = float(pred_probs[class_id])
+    class_name = CLASS_NAMES.get(class_id, f"未知类别({class_id})")
+
+    # 对于 小堆料/大堆料 使用加权逻辑
+    if class_id in [1, 2]:
+        final_class, score, p1, p2 = weighted_small_large(pred_probs, threshold=threshold)
+    else:
+        final_class = class_name
+        score = confidence
+        p1 = float(pred_probs[1])
+        p2 = float(pred_probs[2])
+
+    return final_class, score, p1, p2
+
+
+# ---------------------------
+# 批量推理主函数（保存原图，不改名）
+# ---------------------------
+def batch_classify_images(model_path, input_folder, output_root, roi_file, target_size=640, threshold=0.5):
+    # 加载模型
+    print("🚀 加载模型...")
+    model = YOLO(model_path)
+
+    # 确保输出根目录存在
+    output_root = Path(output_root)
+    output_root.mkdir(parents=True, exist_ok=True)
+    print(f"📁 输出目录: {output_root}")
+
+    # 为所有类别创建子目录
+    class_dirs = {}
+    for name in CLASS_NAMES.values():
+        d = output_root / name
+        d.mkdir(exist_ok=True)
+        class_dirs[name] = d
+
+    # 加载 ROI 区域
+    rois = load_global_rois(roi_file)
+    if not rois:
+        print("❌ 没有有效 ROI，退出程序")
+        return
+
+    print(f"🎯 已加载 {len(rois)} 个 ROI 区域")
+
+    # 定义缺陷严重性等级（数字越小越严重）
+    severity_rank = {
+        "未堆料": 0,
+        "大堆料": 1,
+        "小堆料": 2,
+        "未浇筑满": 3,
+        "浇筑满": 4
+    }
+
+    # 遍历输入文件夹中的所有图片
+    input_folder = Path(input_folder)
+    image_extensions = {'.jpg', '.jpeg', '.png', '.bmp', '.tif', '.tiff'}
+
+    processed_count = 0
+    for img_path in input_folder.glob("*.*"):
+        if img_path.suffix.lower() not in image_extensions:
+            continue
+
+        try:
+            print(f"\n📄 处理: {img_path.name}")
+            img = cv2.imread(str(img_path))
+            if img is None:
+                print(f"❌ 无法读取图像: {img_path.name}")
+                continue
+
+            # 裁剪并缩放 ROI
+            crops = crop_and_resize(img, rois, target_size)
+
+            if not crops:
+                print(f"⚠️ 无有效 ROI 裁剪区域: {img_path.name}")
+                continue
+
+            detected_classes = []
+
+            # 遍历每个 ROI 进行分类
+            for roi_img, roi_idx in crops:
+                final_class, score, p1, p2 = classify_image_weighted(roi_img, model, threshold=threshold)
+                detected_classes.append(final_class)
+                print(f"   🔍 ROI{roi_idx}: {final_class} (score={score:.2f})")
+
+            # 选择最严重的类别
+            most_severe_class = min(detected_classes, key=lambda x: severity_rank.get(x, 99))
+
+            # 构造目标路径：保持原文件名
+            dst_path = class_dirs[most_severe_class] / img_path.name
+
+            # 保存原图（不修改内容，不重命名）
+            cv2.imwrite(str(dst_path), img)
+            print(f"✅ 保存 -> [{most_severe_class}] {dst_path}")
+
+            processed_count += 1
+
+        except Exception as e:
+            print(f"❌ 处理失败 {img_path.name}: {e}")
+
+    print(f"\n🎉 批量处理完成！共处理 {processed_count} 张图像。")
+
+
+# ---------------------------
+# 使用示例（请根据实际情况修改路径）
+# ---------------------------
+if __name__ == "__main__":
+    # 🔧 用户配置区
+    model_path = "/home/hx/yolo/ultralytics_yolo11-main/runs/train/cls_resize/exp_cls2/weights/best.pt"
+    input_folder = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/1000"
+    output_root = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/1000/classified"
+    roi_file = "./roi_coordinates/1_rois.txt"
+    target_size = 640
+    threshold = 0.4  # 小堆料 vs 大堆料的加权阈值
+
+    # 🚀 开始执行
+    batch_classify_images(
+        model_path=model_path,
+        input_folder=input_folder,
+        output_root=output_root,
+        roi_file=roi_file,
+        target_size=target_size,
+        threshold=threshold
+    )