Finishing up commits before moving to Github as main repo

Dockerfile

@@ -1,10 +1,8 @@
 # Use an official Python runtime as a parent image
 FROM python:3.12
+# FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04
 
-# Set the working directory in the container
-WORKDIR /app
-
-# Install system dependencies required by OpenCV and other packages, plus Redis
+# run updates before switching over to non-root user
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libgl1 \
     libglib2.0-0 \
@@ -13,21 +11,40 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libxext6 \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy the requirements file into the container at /app
-COPY requirements.txt .
+# add new user with ID 1000 to avoid permission issues on HF spaces
+RUN useradd -m -u 1000 user
+USER user
+
+# Set home to user's home dir and add local bin to PATH
+ENV HOME=/home/user \
+    PATH=/user/user/.local/bin:$PATH
+
+# Set the working directory in the container
+WORKDIR $HOME/app
+
+# Try and run pip command after setting the user with `USER user` to avoid permission issues with Python
+# NOTE - this is from the HF Spaces docs, not sure if necessary
+COPY --chown=user ./requirements.txt .
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
 
 # Install any needed packages specified in requirements.txt
 # --no-cache-dir: Disables the cache to reduce image size.
 # -r requirements.txt: Specifies the file containing the list of packages to install.
-RUN pip install --no-cache-dir -r requirements.txt
+# RUN pip install --no-cache-dir -r requirements.txt
+
+# Create the necessary dirs
+# we should not need to chown, since we are using USER user above
+RUN mkdir -p uploads results annotated .yolo_config
 
-# Create directories for uploads and results, and set permissions
-RUN mkdir -p /app/uploads /app/results /app/annotated && \
-    chmod 777 /app/uploads /app/results /app/annotated
+# set the env var for YOLO user config directory
+ENV YOLO_CONFIG_DIR=.yolo_config
 
 # Copy the rest of the application code into the container at /app
 # This includes app.py, nemaquant.py, templates/, static/, etc.
-COPY . .
+# COPY . .
 
 # Make port 7860 available to the world outside this container
 # This is the port Flask will run on (as configured in app.py)
@@ -41,4 +58,4 @@ EXPOSE 7860
 # Use gunicorn for production deployment if preferred over Flask's development server
 # CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app"]
 # For simplicity during development and typical HF Spaces use:
-CMD python app.py 
+CMD ["python", "app.py"]

app.py

@@ -9,8 +9,9 @@ import cv2
 import csv
 import pickle
 import shutil
+import logging
 from ultralytics import YOLO
-from ultralytics.utils import ThreadingLocked
+# from ultralytics.utils import ThreadingLocked
 import numpy as np
 import pandas as pd
 from torch import cuda
@@ -23,11 +24,14 @@ from datetime import datetime
 from werkzeug.utils import secure_filename
 from yolo_utils import detect_in_image
 
-set_start_method('spawn')
-
 app = Flask(__name__)
 app.secret_key = os.environ.get('FLASK_SECRET_KEY', str(uuid.uuid4()))  # For session security
 
+# disable werkzeug logging - too noisy
+# comment out these lines if you want to see full logs
+log = logging.getLogger('werkzeug')
+log.setLevel(logging.ERROR)
+
 APP_ROOT = Path(__file__).parent
 UPLOAD_FOLDER = APP_ROOT / 'uploads'
 RESULTS_FOLDER = APP_ROOT / 'results'
@@ -44,6 +48,9 @@ app.config['ALLOWED_EXTENSIONS'] = {'png', 'jpg', 'jpeg', 'tif', 'tiff'}
 # RESULTS_FOLDER.mkdir(parents=True, exist_ok=True)
 # ANNOT_FOLDER.mkdir(parents=True, exist_ok=True)
 
+# Load model once at startup, use CUDA if available
+MODEL_DEVICE = 'cuda' if cuda.is_available() else 'cpu'
+
 # need a global dict to hold async results objects
 # so you can check the progress of an abr
 # maybe there's a better way around this?
@@ -62,9 +69,6 @@ def handle_exception(e):
 def index():
     return render_template('index.html')
 
-# Load model once at startup, use CUDA if available
-MODEL_DEVICE = 'cuda' if cuda.is_available() else 'cpu'
-
 # save the uploaded files
 @app.route('/uploads', methods=['POST'])
 def upload_files():
@@ -389,6 +393,15 @@ def export_csv():
         print(error_message)
         return jsonify({"error": "Server error", "log": error_message}), 500
 
+@app.before_request
+def ensure_session():
+    if 'id' not in session:
+        session['id'] = uuid.uuid4().hex
+        print(f"New session started: {session['id']}")
+    else:
+        pass
+        # print(f"Existing session: {session['id']}")
+
 
 def print_startup_info():
     print("----- NemaQuant Flask App Starting -----")
@@ -406,7 +419,7 @@ def print_startup_info():
 
     is_container = Path('/.dockerenv').exists() or 'DOCKER_HOST' in os.environ
     print(f"Running in container: {is_container}")
-    
+
     if is_container:
         try:
             user_info = f"{os.getuid()}:{os.getgid()}"
@@ -425,15 +438,10 @@ def print_startup_info():
             else:
                 print(f"Directory {path_str} does not exist.")
 
-
-@app.before_request
-def startup_routine():
-    # Ensure session id exists
-    if 'id' not in session:
-        session['id'] = str(uuid.uuid4())
+    # some cleanup steps - not sure quite where to put these
     print('Running periodic cleanup of old sessions...')
     # Cleanup old session folders
-    max_age_hours = 24
+    max_age_hours = 4
     now = time.time()
     for base_dir in [UPLOAD_FOLDER, RESULTS_FOLDER, ANNOT_FOLDER]:
         for session_dir in Path(base_dir).iterdir():
@@ -441,6 +449,11 @@ def startup_routine():
                 mtime = session_dir.stat().st_mtime
                 if now - mtime > max_age_hours * 3600:
                     shutil.rmtree(session_dir)
+    
+    print('App is running at the following local addresses:',
+          'http://127.0.0.1:7860⁠',
+          'http://localhost:7860⁠',
+          sep='\n')
 
 if __name__ == '__main__':
     print_startup_info()

requirements.txt

@@ -5,5 +5,6 @@ pandas==2.3.1
 Pillow==11.3.0
 torch==2.7.1
 ultralytics==8.3.170
+watchdog==6.0.0
 Werkzeug==3.1.3
 gunicorn==21.2.0