update

Dockerfile

@@ -11,6 +11,8 @@ WORKDIR /app
 
 COPY --chown=user ./requirements.txt requirements.txt
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
+RUN pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
+RUN pip install torchxrayvision
 
 COPY --chown=user . /app
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -1,7 +1,32 @@
-from fastapi import FastAPI
+from fastapi import FastAPI,Query,HTTPException
+import torchxrayvision as xrv
+import skimage, torch, torchvision
+import requests
 
-app = FastAPI()
 
+app = FastAPI()
+model = xrv.models.DenseNet(weights="densenet121-res224-all")
 @app.get("/")
 def greet_json():
     return {"Hello": "World!"}
+
+@app.get('/predict')
+def predict(image_url:str = Query(..., description="URL to a chest X-ray image")):
+    try:
+        img = skimage.io.imread(image_url)
+        img = xrv.datasets.normalize(img,255)
+        img = img.mean(2)[None, ...]
+        transform = torchvision.transforms.Compose([xrv.datasets.XRayCenterCrop(),xrv.datasets.XRayResizer(224)])
+        img = transform(img)
+        img = torch.from_numpy(img)
+        outputs = model(img[None,...])
+        prediction = dict(zip(model.pathologies,outputs[0].detach().numpy().tolist()))
+        pred_output = {}
+        for k,v in prediction.items():
+            pred_output.update({k:round(v,2)})
+
+
+        return {"prediction_result":pred_output}
+    except Exception as e:
+        print(e)
+        raise HTTPException(status_code=400, detail=f"Failed to fetch/process image: {str(e)}")

requirements.txt

@@ -1,2 +1,2 @@
 fastapi
-uvicorn[standard]
+uvicorn[standard]