Upload 3 files

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+tags:
+- computer-vision
+- image-segmentation
+- welding
+- weld-inspection
+- yolo
+---
+
+# WeldVision Ensemble
+
+Four-model YOLO segmentation ensemble for weld-surface defect inspection.
+
+## Models
+
+- `weights/best.pt`
+- `weights/best_v0.pt`
+- `weights/crack_specialist.pt`
+- `weights/spatters_specialist.pt`
+
+Inference runs **locally** after downloading the weights from the Hugging Face
+Hub. No Hugging Face Inference Endpoint is required.
+
+## Install
+
+```bash
+pip install ultralytics huggingface_hub opencv-python-headless numpy
+```
+
+## Use
+
+```python
+from weldvision import WeldVision
+
+model = WeldVision.from_pretrained(
+    "bhavibhatt/weldvision-ensemble"
+)
+
+result = model.predict("weld.jpg")
+
+print(result)
+```
+
+The first call downloads and caches the four weights. Subsequent calls reuse the
+local Hugging Face cache.
+
+## Important
+
+This is a proof-of-concept weld surface inspection system. The score and
+PASS/REVIEW/FAIL rules are prototype decision logic and are not welding-code
+acceptance criteria or a substitute for qualified human inspection.

config.json

@@ -0,0 +1,13 @@
+{
+  "model": "WeldVision-Ensemble",
+  "version": "1.0",
+  "weights": [
+    "weights/best.pt",
+    "weights/best_v0.pt",
+    "weights/crack_specialist.pt",
+    "weights/spatters_specialist.pt"
+  ],
+  "confidence": 0.25,
+  "ensemble_mask_iou": 0.5,
+  "imgsz": 640
+}

requirements.txt

@@ -0,0 +1,4 @@
+ultralytics==8.4.126
+huggingface_hub
+opencv-python-headless
+numpy