Upload 3 files

Dockerfile

@@ -0,0 +1,19 @@
+FROM python:3.9
+
+WORKDIR /app
+
+COPY . /app
+
+RUN pip3 install fastapi uvicorn pydantic ultralytics pillow
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+ PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,44 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from ultralytics import YOLO
+from PIL import Image
+import io
+import base64
+
+app = FastAPI()
+
+# Load the YOLO model
+model = YOLO(r'best.pt')
+
+class ImageData(BaseModel):
+    image_base64: str
+
+@app.post("/process_image/")
+async def process_image(data: ImageData):
+    try:
+        # Decode the base64 string to an image
+        image_data = base64.b64decode(data.image_base64)
+        image = Image.open(io.BytesIO(image_data))
+
+        # Process the image with YOLO
+        results = model(image)
+        result = results[0]
+
+        # Extract bounding boxes and confidence scores
+        boxes = result.boxes.xyxy  # Bounding box coordinates
+        scores = result.boxes.conf  # Confidence scores
+
+        if len(boxes) > 0:
+            # Get the index of the bounding box with the highest score
+            highest_score_idx = scores.argmax()
+            # Extract the bounding box with the highest score
+            highest_score_box = boxes[highest_score_idx].tolist()
+            x1, y1, x2, y2 = map(int, highest_score_box)  # Convert to integers
+        else:
+            # If no boxes, return the whole image dimensions
+            x1, y1, x2, y2 = 0, 0, image.width, image.height
+
+        return {"x1": x1, "y1": y1, "x2": x2, "y2": y2}
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10420dfe7db4c88e5bd446f604c3b97e99322962e22e1898ad4d2f325e9b2a3a
+size 52177122