更新液面diff代码

zhuangtai_class_cls_1980x1080_61/.idea/.gitignore

@@ -0,0 +1,5 @@
+# 默认忽略的文件
+/shelf/
+/workspace.xml
+# 基于编辑器的 HTTP 客户端请求
+/httpRequests/

zhuangtai_class_cls_1980x1080_61/.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

zhuangtai_class_cls_1980x1080_61/.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.10" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10" project-jdk-type="Python SDK" />
+</project>

zhuangtai_class_cls_1980x1080_61/.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/zhuangtai_class_cls.iml" filepath="$PROJECT_DIR$/.idea/zhuangtai_class_cls.iml" />
+    </modules>
+  </component>
+</project>

zhuangtai_class_cls_1980x1080_61/.idea/zhuangtai_class_cls.iml

@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.10" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>

zhuangtai_class_cls_1980x1080_61/README.md

@@ -0,0 +1,78 @@
+# RKNN 堆料分类推理系统 README
+
+本项目用于在 RK3588 平台上运行 RKNN 分类模型，对多个 ROI 区域进行堆料状态分类，包括：
+
+未堆料     0
+小堆料     1
+大堆料     2 
+未浇筑满   3
+浇筑满     4
+
+项目中支持 多 ROI 裁剪、模型推理、加权判断（小/大堆料） 和分类结果输出。
+
+## 目录结构
+
+project/
+│── yiliao_cls.rknn                # RKNN 模型
+│── best.pt                        # pt 模型
+│── roi_coordinates/         # ROI 坐标文件目录
+│     └── 1_rois.txt
+│── test_image/              # 测试图片目录
+│     └── 1.jpg
+      └── 2.jpg
+      └── 3.jpg
+│── yiliao_main_rknn.py        # RKNN主推理脚本
+│── yiliao_main_pc.py          # PC推理脚本 
+│── README.md
+
+
+## 配置（略）
+## 安装依赖（略）
+
+
+## 调用示例
+单张图片推理调用示例
+
+```bash
+
+from yiliao_main_rknn import classify_frame_with_rois
+
+#                   示例调用
+# =====================================================
+if __name__ == "__main__":
+    model_path = "yiliao_cls.rknn"
+    roi_file = "./roi_coordinates/1_rois.txt"
+
+    frame = cv2.imread("./test_image/1.png")
+
+    result = classify_frame_with_single_roi(model_path, frame, roi_file)
+
+    print(result)
+
+```
+
+##小堆料 / 大堆料加权判定说明
+
+模型原始输出中，小堆料（class 1）与大堆料（class 2）相比时容易出现概率接近的情况。
+
+通过加权机制：
+
+✔ 可以避免因整体概率偏低导致分类不稳定
+✔ 优先放大“大堆料 的可能性”（因为 w2 > w1）
+✔ score 更能反映堆料大小的趋势，而不是绝对概率
+
+为提高判断稳定性，采用了加权评分方式：（这些参数都可以根据实际情况在文件中对weighted_small_large中参数进行修改）
+score = (0.3 * p1 + 0.7 * p2) / (p1 + p2)
+score ≥ 0.4 → 大堆料
+score < 0.4 → 小堆料
+
+p1：小堆料概率
+p2：大堆料概率
+score 越接近 1 越倾向于大堆料
+score 越接近 0 越倾向于小堆料
+
+
+
+
+
+

zhuangtai_class_cls_1980x1080_61/roi_coordinates/61_rois.txt

@@ -0,0 +1 @@
+445,540,931,319

zhuangtai_class_cls_1980x1080_61/yiliao_main_pc.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/2.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_1980x1080_61/yiliao_main_rknn.py

@@ -0,0 +1,163 @@
+import os
+import cv2
+import numpy as np
+from rknnlite.api import RKNNLite
+
+# ---------------------------
+# 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"
+}
+
+# ---------------------------
+# RKNN 全局实例（只加载一次）
+# ---------------------------
+_global_rknn = None
+
+def init_rknn_model(model_path):
+    global _global_rknn
+    if _global_rknn is not None:
+        return _global_rknn
+
+    rknn = RKNNLite(verbose=False)
+    ret = rknn.load_rknn(model_path)
+    if ret != 0:
+        raise RuntimeError(f"Load RKNN failed: {ret}")
+
+    ret = rknn.init_runtime(core_mask=RKNNLite.NPU_CORE_0)
+    if ret != 0:
+        raise RuntimeError(f"Init runtime failed: {ret}")
+
+    _global_rknn = rknn
+    print(f"[INFO] RKNN 模型加载成功: {model_path}")
+    return rknn
+
+# ---------------------------
+# 预处理
+# ---------------------------
+def letterbox(image, new_size=640, color=(114,114,114)):
+    h, w = image.shape[:2]
+    scale = min(new_size/h, new_size/w)
+    nh, nw = int(h*scale), int(w*scale)
+    resized = cv2.resize(image, (nw, nh))
+    new_img = np.full((new_size, new_size,3), color, dtype=np.uint8)
+    top = (new_size-nh)//2
+    left = (new_size-nw)//2
+    new_img[top:top+nh, left:left+nw] = resized
+    return new_img
+
+def resize_stretch(image, size=640):
+    return cv2.resize(image, (size, size))
+
+def preprocess_image_for_rknn(img, size=640, resize_mode="stretch", to_rgb=False, normalize=False, layout="NHWC"):
+    if resize_mode=="letterbox":
+        img_box = letterbox(img, new_size=size)
+    else:
+        img_box = resize_stretch(img, size=size)
+    if to_rgb:
+        img_box = cv2.cvtColor(img_box, cv2.COLOR_BGR2RGB)
+    img_f = img_box.astype(np.float32)
+    if normalize:
+        img_f /= 255.0
+    if layout=="NHWC":
+        out = np.expand_dims(img_f, axis=0)
+    else:
+        out = np.expand_dims(np.transpose(img_f,(2,0,1)), axis=0)
+    return out.astype(np.float32)
+
+# ---------------------------
+# 单次 RKNN 推理
+# ---------------------------
+def rknn_classify_preprocessed(input_tensor, model_path):
+    rknn = init_rknn_model(model_path)
+    input_tensor = np.ascontiguousarray(input_tensor.astype(np.float32))
+    outs = rknn.inference([input_tensor])
+    pred = outs[0].reshape(-1).astype(float)
+    class_id = int(np.argmax(pred))
+    return class_id, pred
+
+# ---------------------------
+# ROI
+# ---------------------------
+def load_single_roi(txt_path):
+    if not os.path.exists(txt_path):
+        raise RuntimeError(f"ROI 文件不存在: {txt_path}")
+    with open(txt_path) as f:
+        for line in f:
+            s = line.strip()
+            if not s: continue
+            x,y,w,h = map(int, s.split(','))
+            return (x,y,w,h)
+    raise RuntimeError("ROI 文件为空")
+
+def crop_and_return_roi(img, roi):
+    x,y,w,h = roi
+    h_img, w_img = img.shape[:2]
+    if x<0 or y<0 or x+w>w_img or y+h>h_img:
+        raise RuntimeError(f"ROI 超出图像范围: {roi}")
+    return img[y:y+h, x:x+w]
+
+# ---------------------------
+# class1/class2 加权
+# ---------------------------
+def weighted_small_large(pred, threshold=0.4, w1=0.3, w2=0.7):
+    p1,p2 = float(pred[1]), float(pred[2])
+    total = p1+p2
+    score = (w1*p1 + w2*p2)/total if total>0 else 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
+# ---------------------------
+def classify_single_image(model_path, frame, roi_file,
+                           threshold=0.4,
+                           size=640, resize_mode="stretch",
+                           to_rgb=True, normalize=False, layout="NHWC"):
+    """
+    对单张图像进行分类推理（输入为 OpenCV 图像 ndarray）
+
+    Args:
+        model_path (str): RKNN 模型路径
+        frame (np.ndarray): BGR 格式的 OpenCV 图像 (H, W, 3)
+        roi_file (str): ROI 坐标文件路径（格式：x,y,w,h）
+        ... 其他参数同上 ...
+
+    Returns:
+        dict: 分类结果
+    """
+    if frame is None or frame.size == 0:
+        raise ValueError("❌ 输入图像为空或无效")
+
+    roi = load_single_roi(roi_file)
+    roi_img = crop_and_return_roi(frame, roi)
+    input_tensor = preprocess_image_for_rknn(roi_img, size=size, resize_mode=resize_mode,
+                                             to_rgb=to_rgb, normalize=normalize, layout=layout)
+
+    class_id, pred = rknn_classify_preprocessed(input_tensor, model_path)
+    class_name = CLASS_NAMES.get(class_id, f"未知类别({class_id})")
+    if class_id in [1, 2]:
+        final_class, score, p1, p2 = weighted_small_large(pred, threshold)
+    else:
+        final_class = class_name
+        score = float(pred[class_id])
+        p1, p2 = float(pred[1]), float(pred[2])
+
+    return {"class": final_class, "score": round(score, 4), "p1": round(p1, 4), "p2": round(p2, 4),
+            "raw": pred.tolist()}
+# ---------------------------
+# 示例调用
+# ---------------------------
+if __name__=="__main__":
+    model_path = "yiliao_cls61.rknn"
+    roi_file = "./roi_coordinates/61_rois.txt"
+    image_path = "./test_image/2.png"
+
+    result = classify_single_image(model_path, image_path, roi_file)
+    print("[RESULT]", result)
+