Update app.py

app.py

@@ -7,10 +7,8 @@ from ultralytics import YOLO
 
 # Required libraries: streamlit, opencv-python-headless, ultralytics, Pillow
 
-# Replace with your model URL or local file path
 model_path = 'https://huggingface.co/spaces/tstone87/ccr-colorado/resolve/main/best.pt'
 
-# Configure page layout for Hugging Face Spaces
 st.set_page_config(
     page_title="Fire Watch using AI vision models",
     page_icon="🔥",
@@ -18,22 +16,17 @@ st.set_page_config(
     initial_sidebar_state="expanded"
 )
 
-# Sidebar: Upload file, select confidence and video shortening options.
 with st.sidebar:
     st.header("IMAGE/VIDEO UPLOAD")
-    source_file = st.file_uploader(
-        "Choose an image or video...", type=("jpg", "jpeg", "png", "bmp", "webp", "mp4"))
+    source_file = st.file_uploader("Choose an image or video...", 
+                                   type=("jpg", "jpeg", "png", "bmp", "webp", "mp4"))
     confidence = float(st.slider("Select Model Confidence", 25, 100, 40)) / 100
-    video_option = st.selectbox(
-        "Select Video Shortening Option", 
-        ["Original FPS", "1 fps", "1 frame per 5 seconds", "1 frame per 10 seconds", "1 frame per 15 seconds"]
-    )
+    video_option = st.selectbox("Select Video Shortening Option", 
+                                ["Original FPS", "1 fps", "1 frame per 5 seconds", "1 frame per 10 seconds", "1 frame per 15 seconds"])
     progress_text = st.empty()
     progress_bar = st.progress(0)
-    # Container for our dynamic slider (frame viewer)
-    slider_container = st.empty()
+    slider_container = st.empty()  # For dynamic slider widget
 
-# Main page header and intro images
 st.title("WildfireWatch: Detecting Wildfire using AI")
 col1, col2 = st.columns(2)
 with col1:
@@ -47,7 +40,6 @@ Fires in Colorado present a serious challenge, threatening urban communities, hi
 st.markdown("---")
 st.header("Fire Detection:")
 
-# Create two columns for displaying the upload and results.
 col1, col2 = st.columns(2)
 if source_file:
     if source_file.type.split('/')[0] == 'image':
@@ -60,22 +52,22 @@ if source_file:
 else:
     st.info("Please upload an image or video file to begin.")
 
-# Load YOLO model
 try:
     model = YOLO(model_path)
 except Exception as ex:
     st.error(f"Unable to load model. Check the specified path: {model_path}")
     st.error(ex)
 
-# A container to display the currently viewed frame.
-viewer_slot = st.empty()
+viewer_slot = st.empty()  # Container for currently viewed frame
+
+# Initialize session state for slider value if not already set.
+if "slider_value" not in st.session_state:
+    st.session_state.slider_value = 0
 
-# When the user clicks the detect button...
 if st.sidebar.button("Let's Detect Wildfire"):
     if not source_file:
         st.warning("No file uploaded!")
     elif source_file.type.split('/')[0] == 'image':
-        # Process image input.
         res = model.predict(uploaded_image, conf=confidence)
         boxes = res[0].boxes
         res_plotted = res[0].plot()[:, :, ::-1]
@@ -85,17 +77,13 @@ if st.sidebar.button("Let's Detect Wildfire"):
                 for box in boxes:
                     st.write(box.xywh)
     else:
-        # Process video input.
         processed_frames = []
         frame_count = 0
-
-        # Get video properties.
         orig_fps = vidcap.get(cv2.CAP_PROP_FPS)
         total_frames = int(vidcap.get(cv2.CAP_PROP_FRAME_COUNT))
         width  = int(vidcap.get(cv2.CAP_PROP_FRAME_WIDTH))
         height = int(vidcap.get(cv2.CAP_PROP_FRAME_HEIGHT))
 
-        # Determine sampling interval and output fps based on the option selected.
         if video_option == "Original FPS":
             sample_interval = 1
             output_fps = orig_fps
@@ -118,12 +106,10 @@ if st.sidebar.button("Let's Detect Wildfire"):
         success, image = vidcap.read()
         while success:
             if frame_count % sample_interval == 0:
-                # Run detection on current frame.
                 res = model.predict(image, conf=confidence)
                 res_plotted = res[0].plot()[:, :, ::-1]
                 processed_frames.append(res_plotted)
 
-                # Update progress.
                 if total_frames > 0:
                     progress_pct = int((frame_count / total_frames) * 100)
                     progress_text.text(f"Processing frame {frame_count} / {total_frames} ({progress_pct}%)")
@@ -131,35 +117,30 @@ if st.sidebar.button("Let's Detect Wildfire"):
                 else:
                     progress_text.text(f"Processing frame {frame_count}")
 
-                # Update slider only if we have at least one processed frame.
-                if len(processed_frames) > 0:
-                    # Clear previous slider widget.
-                    slider_container.empty()
-                    # Use the slider widget's own value from session_state, or default to the last frame.
-                    default_val = st.session_state.get("frame_slider", len(processed_frames)-1)
-                    # Ensure default value is within bounds.
-                    if default_val > len(processed_frames)-1:
-                        default_val = len(processed_frames)-1
-                    # Create the slider. The key "frame_slider" will automatically update st.session_state.
+                # Only update the slider if we have frames.
+                if processed_frames:
+                    slider_container.empty()  # Clear previous slider
+                    # Use stored slider_value if within bounds, otherwise default to last frame.
+                    default_val = st.session_state.slider_value if st.session_state.slider_value < len(processed_frames) else len(processed_frames)-1
+                    # Create slider with a unique key based on number of processed frames.
                     slider_val = slider_container.slider(
                         "Frame Viewer", 
                         min_value=0, 
                         max_value=len(processed_frames)-1, 
                         value=default_val, 
                         step=1, 
-                        key="frame_slider"
+                        key=f"frame_slider_{len(processed_frames)}"
                     )
-                    # If the user is at the most recent frame, update the viewer.
+                    st.session_state.slider_value = slider_val
+
                     if slider_val == len(processed_frames)-1:
                         viewer_slot.image(processed_frames[-1], caption=f"Frame {len(processed_frames)-1}", use_column_width=True)
             frame_count += 1
             success, image = vidcap.read()
 
-        # Finalize progress.
         progress_text.text("Video processing complete!")
         progress_bar.progress(100)
 
-        # Create and provide the downloadable shortened video.
         if processed_frames:
             temp_video_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4')
             fourcc = cv2.VideoWriter_fourcc(*'mp4v')