moved gradcam inside app

app.py

@@ -2,41 +2,41 @@ import gradio as gr
 import numpy as np
 from app.predictor import predict_disease, compute_ai_risk
 from app.gradcam import generate_gradcam
-import torch
 
 
 def predict(image):
     if image is None:
         return "Upload image first", None
 
-    # Prediction
     label, confidence, tensor, original = predict_disease(image)
 
-    # GradCAM (FIXED CALL)
+    # GradCAM
     heatmap = generate_gradcam(tensor, label)
 
+    # ensure numpy
     heatmap = np.array(heatmap)
 
-    # normalize safely
+    # safe normalization
+    heatmap = heatmap.astype(np.float32)
+
     if heatmap.max() > 1:
         heatmap = heatmap / 255.0
 
     heatmap = np.clip(heatmap, 0, 1)
     heatmap = (heatmap * 255).astype(np.uint8)
 
+    # ensure RGB format
     if len(heatmap.shape) == 2:
-        heatmap = np.stack([heatmap] * 3, axis=-1)
+        heatmap = np.stack([heatmap]*3, axis=-1)
 
-    # Risk
     risk = compute_ai_risk(label, confidence, heatmap)
 
-    report = f"""
-🫀 CardioGuard AI Report
-
-Disease: {label}
-Confidence: {confidence*100:.2f}%
-Risk: {risk}
-"""
+    report = (
+        "🫀 CardioGuard AI Report\n\n"
+        f"Disease: {label}\n"
+        f"Confidence: {confidence*100:.2f}%\n"
+        f"Risk: {risk}"
+    )
 
     return report, heatmap
 
@@ -46,13 +46,24 @@ demo = gr.Blocks()
 with demo:
     gr.Markdown("# 🫀 CardioGuard AI")
 
-    img = gr.Image(type="pil")
+    with gr.Row():
+        img = gr.Image(type="pil")
+        out2 = gr.Image()
+
+    out1 = gr.Textbox(label="Report")
+
     btn = gr.Button("Analyze")
 
-    out1 = gr.Textbox()
-    out2 = gr.Image()
+    btn.click(
+        fn=predict,
+        inputs=img,
+        outputs=[out1, out2]
+    )
 
-    btn.click(predict, img, [out1, out2])
 
+demo.queue()
 
-demo.launch(share=True)
+demo.launch(
+    server_name="0.0.0.0",
+    server_port=7860
+)

main.py

@@ -1,58 +0,0 @@
-print("STEP 1: main.py starting import")
-
-from fastapi import FastAPI, UploadFile, File
-print("STEP 2: fastapi imported")
-
-from app.model_loader import load_all_models
-print("STEP 3: model_loader imported")
-
-from app.predictor import run_full_pipeline
-print("STEP 4: predictor imported")
-
-
-
-from fastapi import FastAPI, UploadFile, File
-import numpy as np
-import cv2
-
-from app.model_loader import load_all_models
-from app.predictor import run_full_pipeline
-
-app = FastAPI(title="CardioGuard AI API")
-
-# 🔥 LOAD MODELS WHEN SERVER STARTS
-@app.on_event("startup")
-def startup_event():
-    load_all_models()
-
-
-# 🩺 Health check route
-@app.get("/")
-def root():
-    return {"message": "CardioGuard API is running"}
-
-
-# ❤️‍🔥 Prediction Route
-@app.post("/predict")
-async def predict_xray(file: UploadFile = File(...)):
-
-    image_bytes = await file.read()
-
-    # convert bytes → PIL image
-    from PIL import Image
-    import io
-    image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
-
-    result = run_full_pipeline(image)
-
-    # convert heatmap image → base64 (so frontend can display)
-    import base64
-    _, buffer = cv2.imencode(".png", result["heatmap"])
-    heatmap_base64 = base64.b64encode(buffer).decode("utf-8")
-
-    return {
-        "disease": result["disease"],
-        "confidence": result["confidence"],
-        "risk": result["risk"],
-        "heatmap": heatmap_base64
-    }

requirements.txt

@@ -1,4 +1,5 @@
-gradio==4.44.1
+gradio==4.29.0
+gradio-client==1.3.0
 
 fastapi==0.110.0
 uvicorn==0.27.1
@@ -6,13 +7,12 @@ uvicorn==0.27.1
 torch
 torchvision
 
-numpy
+numpy<2
 pillow
 opencv-python-headless
 scikit-learn
 joblib
 
 safetensors>=0.4.0
-
 huggingface_hub>=0.25.2,<1.0
 spaces