Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,66 +1,22 @@
-import os
-os.environ["STREAMLIT_CONFIG_DIR"] = "/tmp/.streamlit"
-os.environ["STREAMLIT_SECRETS_FILE"] = "/tmp/.streamlit/secrets.toml"
-
 import streamlit as st
-import pickle
 import numpy as np
 import cv2
 
-# ------------------------------
-# Load saved models
-# ------------------------------
-with open("src/pca_model.pkl", "rb") as f:
-    pca = pickle.load(f)
-
-with open("src/svc_model.pkl", "rb") as f:
-    svc = pickle.load(f)
-
-with open("src/scaler.pkl", "rb") as f:
-    scaler = pickle.load(f)
+st.title("🔍 Dummy Image Upload Test")
 
-# ------------------------------
-# Label mapping
-# ------------------------------
-label_map = {
-    0: "fresh apple",
-    1: "fresh banana",
-    2: "fresh orange",
-    3: "rotten apple",
-    4: "rotten banana",
-    5: "rotten orange"
-}
-
-# ------------------------------
-# Streamlit UI
-# ------------------------------
-st.set_page_config(page_title="Fruit Image Classification", layout="centered")
-st.title("🍎 Fruit Image Classification")
-st.write("Upload an image of a fruit (fresh or rotten) to get the prediction.")
-
-# ------------------------------
-# File uploader
-# ------------------------------
-uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+uploaded_file = st.file_uploader("Upload an image...", type=["jpg", "jpeg", "png"])
 
 if uploaded_file is not None:
-    # Read image as OpenCV BGR
+    # Read file into OpenCV format
     file_bytes = np.asarray(bytearray(uploaded_file.read()), dtype=np.uint8)
-    img = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
-
-    # Convert BGR → RGB for display
-    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
-    st.image(img_rgb, caption="Uploaded Image", use_container_width=True)
+    img = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)  # decode image
 
-    # ------------------------------
-    # Preprocess & predict
-    # ------------------------------
-    img_resized = cv2.resize(img, (64, 64))
-    img_flat = img_resized.flatten().reshape(1, -1)
-    img_scaled = scaler.transform(img_flat)
-    img_pca = pca.transform(img_scaled)
-    pred = svc.predict(img_pca)[0]
-    label = label_map.get(pred, "Unknown")
+    if img is None:
+        st.error("❌ OpenCV failed to load the image. (cv2.imdecode returned None)")
+    else:
+        # Show original BGR and converted RGB
+        st.image(img, channels="BGR", caption="Uploaded Image (BGR)", use_container_width=True)
+        st.image(cv2.cvtColor(img, cv2.COLOR_BGR2RGB), caption="Uploaded Image (RGB)", use_container_width=True)
 
-    # Show prediction
-    st.success(f"Predicted Class: {label}")
+        # Show shape info
+        st.write("Image shape:", img.shape)