Update app (1).py

app (1).py

@@ -6,8 +6,7 @@ from tensorflow.keras.applications.resnet50 import preprocess_input, decode_pred
 from tensorflow.keras.preprocessing import image
 import cv2
 from PIL import Image
-import io
-import matplotlib.pyplot as plt
+import os
 
 # Load pre-trained model
 model = ResNet50(weights='imagenet')
@@ -30,38 +29,49 @@ def make_gradcam_heatmap(img_array, model, last_conv_layer_name, pred_index=None
     conv_outputs = conv_outputs[0]
     heatmap = conv_outputs @ pooled_grads[..., tf.newaxis]
     heatmap = tf.squeeze(heatmap)
-
     heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)
     return heatmap.numpy()
 
 # Streamlit UI
-st.title("  Image Classifier + Grad-CAM Visualizer")
+st.title("🧠 Image Classifier + Grad-CAM Visualizer")
+
+# File uploader
+uploaded_file = st.file_uploader("📤 Upload an image (JPG, JPEG, PNG)", type=["jpg", "jpeg", "png"])
+
+# Use default image if no upload
+if uploaded_file is not None:
+    image_ = Image.open(uploaded_file).convert('RGB')
+else:
+    st.info("No image uploaded. Using default image.")
+    default_path = "image_default.jpg"  # Make sure this file exists in your project folder
+    if os.path.exists(default_path):
+        image_ = Image.open(default_path).convert('RGB')
+    else:
+        st.error("Default image not found. Please upload an image.")
+        st.stop()
 
-uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
-if uploaded_file:
-    # Load and preprocess image
-    img = Image.open(uploaded_file).convert('RGB')
-    img_resized = img.resize((224, 224))
-    x = image.img_to_array(img_resized)
-    x = np.expand_dims(x, axis=0)
-    x = preprocess_input(x)
+# Preprocess image
+image_resized = image_.resize((224, 224))
+x = image.img_to_array(image_resized)
+x = np.expand_dims(x, axis=0)
+x = preprocess_input(x)
 
-    # Prediction
-    preds = model.predict(x)
-    pred_class = decode_predictions(preds, top=1)[0][0]
-    st.markdown(f"**Predicted:** `{pred_class[1]}` with `{pred_class[2]*100:.2f}%` confidence")
+# Prediction
+preds = model.predict(x)
+pred_class = decode_predictions(preds, top=1)[0][0]
+st.markdown(f"**Predicted:** `{pred_class[1]}` with `{pred_class[2]*100:.2f}%` confidence")
 
-    # Grad-CAM
-    heatmap = make_gradcam_heatmap(x, model, last_conv_layer_name)
-    img_cv = np.array(img_resized)
-    heatmap = cv2.resize(heatmap, (img_cv.shape[1], img_cv.shape[0]))
-    heatmap = np.uint8(255 * heatmap)
-    heatmap = cv2.applyColorMap(heatmap, cv2.COLORMAP_JET)
-    superimposed_img = cv2.addWeighted(img_cv, 0.6, heatmap, 0.4, 0)
+# Grad-CAM
+heatmap = make_gradcam_heatmap(x, model, last_conv_layer_name)
+img_cv = np.array(image_resized)
+heatmap = cv2.resize(heatmap, (img_cv.shape[1], img_cv.shape[0]))
+heatmap = np.uint8(255 * heatmap)
+heatmap = cv2.applyColorMap(heatmap, cv2.COLORMAP_JET)
+superimposed_img = cv2.addWeighted(img_cv, 0.6, heatmap, 0.4, 0)
 
-    # Display images
-    col1, col2 = st.columns(2)
-    with col1:
-        st.image(img_resized, caption="Original Image", use_container_width=True)
-    with col2:
-        st.image(superimposed_img, caption="Grad-CAM", use_container_width=True)
+# Display images
+col1, col2 = st.columns(2)
+with col1:
+    st.image(image_resized, caption="Original Image", use_container_width=True)
+with col2:
+    st.image(superimposed_img, caption="Grad-CAM", use_container_width=True)