提交数据处理的代码

datadeal/deepfasion2_to_yolo.py

+# coding:utf-8
+import json
+import os
+import os.path
+
+from PIL import Image
+from tqdm import tqdm
+
+
+def listPathAllfiles(dirname):
+    result = []
+    for maindir, subdir, file_name_list in os.walk(dirname):
+        for filename in file_name_list:
+            apath = os.path.join(maindir, filename)
+            result.append(apath)
+    return result
+
+
+if __name__ == '__main__':
+    annos_path = r"E:\06服饰\Deepfashion2\train\train\annos"  # 改成需要路径
+    image_path = r"E:\06服饰\Deepfashion2\train\train\images"  # 改成需要路径
+    labels_path = r"E:\06服饰\Deepfashion2\train\train\labels"  # 改成需要路径
+
+    num_images = len(os.listdir(annos_path))
+
+    for num in tqdm(range(1, num_images + 1)):
+        json_name = os.path.join(annos_path, str(num).zfill(6) + '.json')
+        image_name = os.path.join(image_path, str(num).zfill(6) + '.jpg')
+        txtfile = os.path.join(labels_path, str(num).zfill(6) + '.txt')
+        imag = Image.open(image_name)
+        width, height = imag.size
+
+        res = []
+        with open(json_name, 'r') as f:
+            temp = json.loads(f.read())
+            for i in temp:
+                if i == 'source' or i == 'pair_id':
+                    continue
+                else:
+                    box = temp[i]['bounding_box']
+                    x_1 = round((box[0] + box[2]) / 2 / width, 6)
+                    y_1 = round((box[1] + box[3]) / 2 / height, 6)
+                    w = round((box[2] - box[0]) / width, 6)
+                    h = round((box[3] - box[1]) / height, 6)
+
+                    category_id = int(temp[i]['category_id'] - 1)
+
+                    res.append(" ".join([str(category_id), str(x_1), str(y_1), str(w), str(h)]))
+
+        open(txtfile, "w").write("\n".join(res))
+

demo1.py

 from ultralytics import RTDETR
 from ultralytics import YOLO
 # Load a model
-model = RTDETR("E:/fourworkplace/yolov8v4/ultralytics/cfg/models/v8/yolov8-swinV2-RTVIT.yaml")  # build a new model from scratch
+model = RTDETR("E:/fourworkplace/yolov8v4/ultralytics/cfg/models/v8/yolov8-swinV2-RTViT.yaml")  # build a new model from scratch
 model.info()
 
 model1=RTDETR("E:/fourworkplace/yolov8v4/ultralytics/cfg/models/v8/yolov8-swinV2-RT.yaml")
@@ -12,7 +12,8 @@ model2.info()
 
 
 
-
+model3=RTDETR("E:/fourworkplace/yolov8v4/ultralytics/cfg/models/v3/yolov3-swinV2-RTViT.yaml")
+model3.info()
 
 
 

myfourtrain.py

@@ -35,5 +35,7 @@ model = YOLO("E:/fourworkplace/yolov8v4/ultralytics/cfg/models/v8/yolov8-swinV2-
 model.train(data="E:/fourworkplace/yolov8v4/ultralytics/cfg/datasets/yolov8_four.yaml",
     pretrained=True,epochs=epoch_set,batch=64,patience=200,resume=True,workers=workers_set)
 
+#使用YOLOv3进行训练,并把我们的改进方法加到YOLOv3上面以此突出改进方案的优势。
+
 
 #下面开始考虑对图像分割问题的处理方案

ultralytics/cfg/datasets/yolov8_four.yaml

+
+path: ../datasets/imagenet  # dataset root dir
+train: train  # train images (relative to 'path') 1281167 images
+val: val  # val images (relative to 'path') 50000 images
+test:  # test images (optional)
+
+nc: 13  # number of classes
+names: ['short sleeve top', 'long sleeve top','short sleeve outwear','long sleeve outwear',
+         'vest','sling','shorts','trousers','skirt','short sleeve dress','long sleeve dress',
+         'vest dress','sling dress']

ultralytics/cfg/datasets/yolov8_seg_four.yaml

+
+path: ../datasets/imagenet  # dataset root dir
+train: train  # train images (relative to 'path') 1281167 images
+val: val  # val images (relative to 'path') 50000 images
+test:  # test images (optional)
+
+nc: 13  # number of classes
+names: [ 'short sleeve top', 'long sleeve top','short sleeve outwear','long sleeve outwear',
+         'vest','sling','shorts','trousers','skirt','short sleeve dress','long sleeve dress',
+         'vest dress','sling dress' ]

ultralytics/cfg/models/v3/yolov3-swinV2-RTViT.yaml

+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv3 object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/yolov3
+
+# Parameters
+nc: 13  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, SwinV2_CSPB, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, SwinV2_CSPB, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, SwinV2_CSPB, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, SwinV2_CSPB, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, SwinV2_CSPB, [1024]],  # 10
+  ]
+
+# YOLOv3 head
+head:
+  [[-1, 1, SwinV2_CSPB, [1024, False]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, SwinV2_CSPB, [512, False]],
+   [-1, 1, SwinV2_CSPB, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, SwinV2_CSPB, [256, False]],
+   [-1, 2, SwinV2_CSPB, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, RTDETRDecoderViT, [nc]],   # Detect(P3, P4, P5)
+  ]