Update src/streamlit_app.py

src/streamlit_app.py

@@ -173,10 +173,11 @@ st.set_page_config(page_title="DeepSlide: Landslide Detection", layout="wide")
 st.title("DeepSlide: Landslide Detection")
 st.markdown("""
 ## Instructions
-1. Select a model from the sidebar or choose to run all models.
-2. Upload one or more `.h5` files.
-3. The app will process the files and display the input image, prediction, and overlay.
-4. You can download the prediction results.
+1. **Model Selection**: Choose a single model from the sidebar or select "Run all models".
+2. **Data Input**: 
+   - Try an example image from the dropdown, or
+   - Upload your own .h5 files
+3. **Results**: View predictions and download results as .npy files.
 """)
 
 # Sidebar for model selection
@@ -201,6 +202,30 @@ st.header("Upload Data")
 if 'upload_errors' not in st.session_state:
     st.session_state.upload_errors = []
 
+# Example images selection
+st.subheader("Try Example Images")
+examples_dir = os.path.join(os.path.dirname(os.path.dirname(__file__)), "examples")
+example_files = []
+
+try:
+    if os.path.exists(examples_dir):
+        example_files = [f for f in os.listdir(examples_dir) if f.endswith('.h5')]
+        example_files.sort()
+except:
+    pass
+
+if example_files:
+    selected_example = st.selectbox(
+        "Select an example image to test:",
+        options=["None"] + example_files,
+        help="Choose an example .h5 file to quickly test the models"
+    )
+else:
+    st.info("No example files found")
+    selected_example = "None"
+
+# File upload section
+st.subheader("Upload Your Own Files")
 uploaded_files = st.file_uploader(
     "Choose .h5 files...", 
     type="h5", 
@@ -208,12 +233,63 @@ uploaded_files = st.file_uploader(
     help="Upload your .h5 files here. Maximum file size is 200MB."
 )
 
+def process_h5_file(file_path, file_name):
+    """Process a single h5 file"""
+    try:
+        with h5py.File(file_path, 'r') as hdf:
+            if 'img' not in hdf:
+                st.error(f"Error: 'img' dataset not found in {file_name}")
+                return
+                
+            data = np.array(hdf.get('img'))
+            data[np.isnan(data)] = 0.000001
+            channels = config["dataset_config"]["channels"]
+            
+            image = np.zeros((128, 128, len(channels)))
+            
+            if data.ndim == 3:
+                if data.shape[0] == 14: # (C, H, W)
+                    for i, band in enumerate(channels):
+                        image[:, :, i] = data[band-1, :, :]
+                elif data.shape[2] == 14: # (H, W, C)
+                    for i, band in enumerate(channels):
+                        image[:, :, i] = data[:, :, band-1]
+                else:
+                    st.warning(f"Unexpected data shape: {data.shape}. Assuming (C, H, W).")
+                    for i, band in enumerate(channels):
+                        if band-1 < data.shape[0]:
+                            image[:, :, i] = data[band-1, :, :]
+            else:
+                st.error(f"Data has {data.ndim} dimensions, expected 3.")
+                return
+
+            # Prepare for model (Batch, Channel, Height, Width)
+            image_display = image.transpose(2, 0, 1) # (C, H, W)
+            image_tensor = torch.from_numpy(image_display).unsqueeze(0).float() # (1, C, H, W)
+
+            if model_option == "Select a single model":
+                process_and_visualize(selected_model_key, selected_model_info, image_tensor, image_display, file_name)
+            else:
+                for model_key, model_info in MODEL_DESCRIPTIONS.items():
+                    process_and_visualize(model_key, model_info, image_tensor, image_display, file_name)
+
+    except Exception as e:
+        st.error(f"Error processing file {file_name}: {str(e)}")
+
+# Process example file if selected
+if selected_example != "None":
+    st.write(f"Processing example: {selected_example}")
+    example_path = os.path.join(examples_dir, selected_example)
+    with st.spinner(f'Processing {selected_example}...'):
+        process_h5_file(example_path, selected_example)
+
+# Process uploaded files
 if uploaded_files:
     for uploaded_file in uploaded_files:
         st.write(f"Processing file: {uploaded_file.name}")
         st.write(f"File size: {uploaded_file.size} bytes")
         
-        with st.spinner('Classifying...'):
+        with st.spinner('Processing...'):
             try:
                 # Read the file directly using BytesIO
                 bytes_data = uploaded_file.getvalue()
@@ -228,18 +304,6 @@ if uploaded_files:
                     data[np.isnan(data)] = 0.000001
                     channels = config["dataset_config"]["channels"]
                     
-                    # Prepare image
-                    # Assuming data shape is (14, 128, 128) based on typical satellite data or (128, 128, 14)
-                    # The original code did: image[:, :, i] = data[band-1] implying data is (14, 128, 128) if accessed by index
-                    # But later it did data[:, :, channel-1] in the else block?
-                    # Let's check the original code logic again.
-                    # Original code had two different logic blocks for data loading!
-                    # Block 1 (single model): image[:, :, i] = data[band-1] -> implies data is (C, H, W)
-                    # Block 2 (all models): image[:, :, i] = data[:, :, channel-1] -> implies data is (H, W, C)
-                    
-                    # I will assume (C, H, W) is more standard for HDF5 'img' usually, but let's try to be robust or pick one.
-                    # Given the inconsistency, I'll check data shape.
-                    
                     image = np.zeros((128, 128, len(channels)))
                     
                     if data.ndim == 3:
@@ -259,7 +323,6 @@ if uploaded_files:
                         continue
 
                     # Prepare for model (Batch, Channel, Height, Width)
-                    # image is currently (H, W, C)
                     image_display = image.transpose(2, 0, 1) # (C, H, W)
                     image_tensor = torch.from_numpy(image_display).unsqueeze(0).float() # (1, C, H, W)
 
@@ -275,4 +338,5 @@ if uploaded_files:
                 st.error(traceback.format_exc())
                 continue
 
-st.success('Done!')
+if selected_example != "None" or uploaded_files:
+    st.success('✅ Processing completed!')