Upload trained YOLOv8 PCB model

README.md

@@ -0,0 +1,14 @@
+# PCB Defect Detection (YOLOv8)
+
+Trained YOLOv8 model for PCB defects.
+
+**Files:**
+- best.pt : YOLOv8 weights
+- pcb_defects.yaml : dataset config (classes)
+
+**Usage (example):**
+```python
+from ultralytics import YOLO
+model = YOLO("https://huggingface.co/<USERNAME>/pcb-defect-detector/resolve/main/best.pt")
+model("pcb.jpg")
+```

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9adaae5a5cd29f5f721715b26be248ed667edea24acb9f4819ca186abd4ce2e0
+size 22518954

pcb_defects.yaml

@@ -0,0 +1,13 @@
+# PCB Defects Dataset YAML configuration
+# Total images: 10,668 (Train: 8,534, Val: 2,134)
+# Defect classes: 6
+
+path: /content/PCB_YOLO_Dataset  # dataset root dir
+train: images/train   # train images (relative to 'path')
+val: images/val       # val images (relative to 'path')
+
+# Number of classes
+nc: 6
+
+# Class names
+names: {0: 'missing_hole', 1: 'mouse_bite', 2: 'open_circuit', 3: 'short', 4: 'spur', 5: 'spurious_copper'}