Add mold detection Streamlit frontend v5

app.py

@@ -6,8 +6,6 @@ from PIL import Image
 # CONFIG
 # ==============================
 API_BASE = "https://AdarshDS-mold-detection-api.hf.space"
-
-RESNET_API   = f"{API_BASE}/predict/resnet"
 CONVNEXT_API = f"{API_BASE}/predict/v2"
 
 st.set_page_config(
@@ -19,11 +17,12 @@ st.set_page_config(
 # UI HEADER
 # ==============================
 st.title("🦠 AI Mold Detection System")
-st.caption("Dual-model analysis using ResNet (Baseline) and ConvNeXt (Advanced)")
+st.caption("Powered by ConvNeXt (Advanced Model)")
 
 st.write(
     "Upload an image of a wall or ceiling. "
-    "The system evaluates the image using two independent AI models."
+    "The image is analyzed using an advanced ConvNeXt-based AI model "
+    "with uncertainty estimation and self-supervised verification."
 )
 
 file = st.file_uploader(
@@ -44,85 +43,54 @@ if file:
             "file": (file.name, file_bytes, file.type)
         }
 
-        with st.spinner("🔍 Analyzing image with both models..."):
-            resnet_resp   = requests.post(RESNET_API, files=files_payload)
-            convnext_resp = requests.post(CONVNEXT_API, files=files_payload)
+        with st.spinner("🔍 Analyzing image..."):
+            resp = requests.post(CONVNEXT_API, files=files_payload)
 
         st.markdown("---")
-        st.subheader("📊 Model Predictions")
-
-        cols = st.columns(2)
-
-        # ==============================
-        # ResNet Results
-        # ==============================
-        with cols[0]:
-            st.subheader("🔹 ResNet (Baseline)")
-
-            if resnet_resp.status_code != 200:
-                st.warning("⚠️ ResNet model unavailable.")
-            else:
-                res = resnet_resp.json()
-
-                st.metric("Decision", res["decision"])
-                st.metric("Mold Probability", res["mold_probability"])
-                st.metric("Biological Probability", res["biological_probability"])
-
-                if res["decision"] == "Mold":
-                    st.error("❌ Mold detected (ResNet).")
-                elif res["decision"] == "Possible Mold":
-                    st.warning("⚠️ Possible mold detected (ResNet).")
-                else:
-                    st.success("✅ No mold detected (ResNet).")
-
-        # ==============================
-        # ConvNeXt Results
-        # ==============================
-        with cols[1]:
-            st.subheader("🔹 ConvNeXt (Advanced)")
-
-            if convnext_resp.status_code != 200:
-                st.error("❌ ConvNeXt API error.")
-                st.text(convnext_resp.text)
-            else:
-                res = convnext_resp.json()
-
-                st.metric("Decision", res["decision"])
-                st.metric(
-                    "Mold Probability",
-                    res["model_outputs"]["mold_probability"]
+        st.subheader("📊 Prediction Result")
+
+        if resp.status_code != 200:
+            st.error("❌ API error while analyzing the image.")
+            st.text(resp.text)
+        else:
+            res = resp.json()
+
+            # ==============================
+            # Main Results
+            # ==============================
+            st.metric("Decision", res["decision"])
+            st.metric(
+                "Mold Probability",
+                res["model_outputs"]["mold_probability"]
+            )
+            st.metric(
+                "Biological Probability",
+                res["model_outputs"]["biological_probability"]
+            )
+
+            # ==============================
+            # Confidence Checks
+            # ==============================
+            st.subheader("📈 Confidence Checks")
+            cc = res["confidence_checks"]
+
+            c1, c2, c3 = st.columns(3)
+            c1.metric("Uncertainty", cc["uncertainty"])
+            c2.metric("Patch Ratio", cc["patch_ratio"])
+            c3.metric("DINO Similarity", cc["dino_similarity"])
+
+            # ==============================
+            # User Feedback
+            # ==============================
+            if res["decision"] == "Mold":
+                st.error(
+                    "❌ Mold detected. "
+                    "Professional remediation is strongly recommended."
                 )
-                st.metric(
-                    "Biological Probability",
-                    res["model_outputs"]["biological_probability"]
+            elif res["decision"] == "Possible Mold":
+                st.warning(
+                    "⚠️ Possible mold detected. "
+                    "Human inspection is advised."
                 )
-
-                cc = res["confidence_checks"]
-                st.caption("Confidence checks")
-                c1, c2, c3 = st.columns(3)
-                c1.metric("Uncertainty", cc["uncertainty"])
-                c2.metric("Patch Ratio", cc["patch_ratio"])
-                c3.metric("DINO Similarity", cc["dino_similarity"])
-
-                if res["decision"] == "Mold":
-                    st.error("❌ Mold detected (ConvNeXt). Professional remediation recommended.")
-                elif res["decision"] == "Possible Mold":
-                    st.warning("⚠️ Possible mold detected (ConvNeXt). Human inspection advised.")
-                else:
-                    st.success("✅ No mold detected (ConvNeXt).")
-
-        # ==============================
-        # Comparison Insight (Optional)
-        # ==============================
-        try:
-            if resnet_resp.ok and convnext_resp.ok:
-                r_dec = resnet_resp.json()["decision"]
-                c_dec = convnext_resp.json()["decision"]
-
-                if r_dec != c_dec:
-                    st.info(
-                        "ℹ️ The two models disagree. "
-                        "ConvNeXt uses uncertainty estimation and self-supervised verification."
-                    )
-        except Exception:
-            pass
+            else:
+                st.success("✅ No mold detected.")