1

README.dataset.txt

@@ -0,0 +1,6 @@
+# vanasoll > 2025-08-22 1:08am
+https://universe.roboflow.com/vanasol1/vanasoll-2r4wh
+
+Provided by a Roboflow user
+License: CC BY 4.0
+

README.roboflow.txt

@@ -0,0 +1,35 @@
+
+vanasoll - v1 2025-08-22 1:08am
+==============================
+
+This dataset was exported via roboflow.com on March 17, 2026 at 6:39 AM GMT
+
+Roboflow is an end-to-end computer vision platform that helps you
+* collaborate with your team on computer vision projects
+* collect & organize images
+* understand and search unstructured image data
+* annotate, and create datasets
+* export, train, and deploy computer vision models
+* use active learning to improve your dataset over time
+
+For state of the art Computer Vision training notebooks you can use with this dataset,
+visit https://github.com/roboflow/notebooks
+
+To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com
+
+The dataset includes 76318 images.
+Objects are annotated in YOLOv8 format.
+
+The following pre-processing was applied to each image:
+* Auto-orientation of pixel data (with EXIF-orientation stripping)
+* Resize to 640x640 (Stretch)
+
+The following augmentation was applied to create 3 versions of each source image:
+* 50% probability of horizontal flip
+* Randomly crop between 0 and 25 percent of the image
+* Random rotation of between -15 and +15 degrees
+* Random brigthness adjustment of between -20 and +20 percent
+* Random exposure adjustment of between -8 and +8 percent
+* Random Gaussian blur of between 0 and 1.4 pixels
+
+

train_yolov8.py

@@ -0,0 +1,49 @@
+from argparse import ArgumentParser
+from pathlib import Path
+
+from ultralytics import YOLO
+
+
+def parse_args():
+    parser = ArgumentParser(description="Train YOLOv8 on this dataset.")
+    parser.add_argument("--model", default="yolov8n.pt", help="Model or checkpoint path.")
+    parser.add_argument("--epochs", type=int, default=100)
+    parser.add_argument("--imgsz", type=int, default=640)
+    parser.add_argument("--batch", type=int, default=8, help="Use -1 for automatic batch size.")
+    parser.add_argument("--device", default="0", help="CUDA device such as 0, or cpu.")
+    parser.add_argument("--workers", type=int, default=4)
+    parser.add_argument("--patience", type=int, default=30)
+    parser.add_argument("--name", default="yolov8n_acne")
+    parser.add_argument("--resume", action="store_true", help="Resume from --model checkpoint.")
+    return parser.parse_args()
+
+
+def main():
+    args = parse_args()
+    root = Path(__file__).resolve().parent
+    data = root / "data.yaml"
+
+    if not data.is_file():
+        raise FileNotFoundError(f"Dataset config not found: {data}")
+
+    model = YOLO(args.model)
+    model.train(
+        data=str(data),
+        epochs=args.epochs,
+        imgsz=args.imgsz,
+        batch=args.batch,
+        device=args.device,
+        workers=args.workers,
+        patience=args.patience,
+        project=str(root / "runs"),
+        name=args.name,
+        pretrained=True,
+        cache=False,
+        amp=True,
+        plots=True,
+        resume=args.resume,
+    )
+
+
+if __name__ == "__main__":
+    main()