bushu

yemian/resize/resize1/test/frame_20250805_121717_22320.txt

@@ -0,0 +1 @@
+0 0.317016 0.412804 0.274836 0.624093 0.466866 0.652477 0.748806 0.636707 0.729938 0.409651 0.482407 0.422264 0.436896 0.425418

yemian/resize/resize1/train/frame_20250805_121723_22500.txt

@@ -0,0 +1 @@
+0 0.314796 0.422264 0.268177 0.620940 0.462427 0.652477 0.756576 0.627247 0.732158 0.409651 0.480187 0.425418 0.432457 0.431725

yemian/resize/resize1/val/frame_20250805_121800_23580.txt

@@ -0,0 +1 @@
+0 0.315906 0.409651 0.274836 0.617786 0.466866 0.643014 0.751026 0.630400 0.733267 0.406497 0.490177 0.422264 0.434676 0.419111

yemian/resize/resize_dataset_image.py

@@ -0,0 +1,52 @@
+import os
+import cv2
+
+# ----------------------------
+# 配置
+# ----------------------------
+SOURCE_DIR = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/seg/resize_seg2"       # 原始图片目录
+TARGET_DIR = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/seg/resize_seg3"    # 输出目录
+TARGET_SIZE = 640           # resize 尺寸
+SUBSETS = ["train", "val", "test"]
+
+# ----------------------------
+# 全局 ROI (x, y, w, h)
+# ----------------------------
+GLOBAL_ROI = [562, 798, 1287, 453]
+
+# ----------------------------
+# 主处理函数
+# ----------------------------
+def process_images():
+    x, y, w, h = GLOBAL_ROI
+    for subset in SUBSETS:
+        src_dir = os.path.join(SOURCE_DIR, subset)
+        tgt_dir = os.path.join(TARGET_DIR, subset)
+        os.makedirs(tgt_dir, exist_ok=True)
+
+        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}/{file}")
+
+if __name__ == "__main__":
+    process_images()

yemian/resize/resize_dataset_label.py

@@ -0,0 +1,93 @@
+import os
+
+# ----------------------------
+# 配置
+# ----------------------------
+SOURCE_DIR = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/seg/resize_seg2"       # 原始图片目录
+TARGET_DIR = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/seg/resize_seg3"    # 输出目录
+SUBSETS = ["train", "val", "test"]
+
+# 全局 ROI (x, y, w, h)
+GLOBAL_ROI = [562, 798, 1287, 453]
+
+# ----------------------------
+# 分割标签处理函数
+# ----------------------------
+def adjust_seg_labels(label_path, crop_coords, orig_size):
+    x1, y1, x2, y2 = crop_coords
+    crop_w = x2 - x1
+    crop_h = y2 - y1
+    new_labels = []
+
+    if not os.path.exists(label_path):
+        print(f"⚠️ 标签源文件不存在: {label_path}")
+        return new_labels
+
+    with open(label_path, 'r') as f:
+        lines = f.readlines()
+
+    orig_w, orig_h = orig_size
+
+    for line in lines:
+        parts = line.strip().split()
+        if len(parts) < 3 or len(parts) % 2 == 0:
+            continue  # 至少类别 + 一个点(x,y)
+
+        cls = parts[0]
+        coords = list(map(float, parts[1:]))
+
+        new_coords = []
+        for i in range(0, len(coords), 2):
+            x = coords[i] * orig_w
+            y = coords[i+1] * orig_h
+            x -= x1
+            y -= y1
+            x_new = x / crop_w
+            y_new = y / crop_h
+            new_coords.extend([x_new, y_new])
+
+        new_line = cls + " " + " ".join([f"{c:.6f}" for c in new_coords])
+        new_labels.append(new_line)
+
+    return new_labels
+
+# ----------------------------
+# 主处理函数
+# ----------------------------
+def process_seg_labels():
+    x, y, w, h = GLOBAL_ROI
+    fixed_roi = (x, y, x + w, y + h)
+
+    for subset in SUBSETS:
+        src_dir = os.path.join(SOURCE_DIR, subset)
+        tgt_dir = os.path.join(TARGET_DIR, subset)
+        os.makedirs(tgt_dir, exist_ok=True)
+
+        for file in os.listdir(src_dir):
+            if not (file.endswith(".txt")):
+                continue
+
+            label_path = os.path.join(src_dir, file)
+            # 读取原图尺寸
+            img_name = os.path.splitext(file)[0] + ".jpg"
+            img_path = os.path.join(src_dir, img_name)
+            if not os.path.exists(img_path):
+                print(f"❌ 无法读取图片以获取尺寸: {img_path}")
+                continue
+
+            import cv2
+            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]
+
+            new_labels = adjust_seg_labels(label_path, fixed_roi, (w_img, h_img))
+            tgt_label_path = os.path.join(tgt_dir, file)
+            with open(tgt_label_path, 'w') as f:
+                f.write("\n".join(new_labels))
+
+            print(f"✅ 标签处理完成: {subset}/{file}, 条数 {len(new_labels)}")
+
+if __name__ == "__main__":
+    process_seg_labels()

yemian/resize/roi_coordinates/1_rois2.txt

@@ -0,0 +1 @@
+562, 798, 1287, 453

yemian/resize/rtest.py

@@ -6,12 +6,12 @@ import numpy as np
 from ultralytics import YOLO
 from pathlib import Path
 
-# ====================== 配置参数 ======================
-MODEL_PATH = "/home/hx/yolo/ultralytics_yolo11-main/runs/train/seg_r/exp2/weights/best.pt"
+# ====================== 配置参数 ======================3
+MODEL_PATH = "best.pt"
 #SOURCE_IMG_DIR = "/home/hx/yolo/output_masks"  # 原始输入图像目录
-SOURCE_IMG_DIR = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/f6"  # 原始输入图像目录
+SOURCE_IMG_DIR = "/home/hx/yolo/yemian/test_image"  # 原始输入图像目录
 OUTPUT_DIR = "/home/hx/yolo/output_masks2"  # 推理输出根目录
-ROI_COORDS_FILE = "./roi_coordinates/1_rois.txt"        # 必须与训练时相同
+ROI_COORDS_FILE = "./roi_coordinates/1_rois2.txt"        # 必须与训练时相同
 CONF_THRESHOLD = 0.25
 IOU_THRESHOLD = 0.45
 DEVICE = "cuda:0" if torch.cuda.is_available() else "cpu"

yemian/resize/test/test/frame_20250805_121717_22320.txt

@@ -0,0 +1 @@
+0 0.378906 0.684028 0.357701 0.750496 0.454241 0.759425 0.595982 0.754464 0.586496 0.683036 0.462054 0.687004 0.439174 0.687996

yemian/resize/test/train/frame_20250805_121723_22500.txt

@@ -0,0 +1 @@
+0 0.377790 0.687004 0.354353 0.749504 0.452009 0.759425 0.599888 0.751488 0.587612 0.683036 0.460938 0.687996 0.436942 0.689980

yemian/resize/test/val/frame_20250805_121800_23580.txt

@@ -0,0 +1 @@
+0 0.378348 0.683036 0.357701 0.748512 0.454241 0.756448 0.597098 0.752480 0.588170 0.682044 0.465960 0.687004 0.438058 0.686012