add a few more metrics to debug

Dockerfile

@@ -38,9 +38,9 @@ RUN apt -qq update && apt -qq install --no-install-recommends -y \
     && apt -qq install --no-install-recommends -y \
         libedgetpu1-max \
     ## Tensorflow lite (python 3.7 only)
-    && wget -q https://dl.google.com/coral/python/tflite_runtime-2.1.0.post1-cp37-cp37m-linux_x86_64.whl \
+    && wget -q https://dl.google.com/coral/python/tflite_runtime-2.1.0-cp37-cp37m-linux_x86_64.whl \
-    && python3.7 -m pip install tflite_runtime-2.1.0.post1-cp37-cp37m-linux_x86_64.whl \
+    && python3.7 -m pip install tflite_runtime-2.1.0-cp37-cp37m-linux_x86_64.whl \
-    && rm tflite_runtime-2.1.0.post1-cp37-cp37m-linux_x86_64.whl \
+    && rm tflite_runtime-2.1.0-cp37-cp37m-linux_x86_64.whl \
     && rm -rf /var/lib/apt/lists/* \
     && (apt-get autoremove -y; apt-get autoclean -y)
 

README.md

@@ -16,6 +16,16 @@ You see multiple bounding boxes because it draws bounding boxes from all frames
 [![](http://img.youtube.com/vi/nqHbCtyo4dY/0.jpg)](http://www.youtube.com/watch?v=nqHbCtyo4dY "Frigate")
 
 ## Getting Started
+Build the container with
+```
+docker build -t frigate .
+```
+
+Models for both CPU and EdgeTPU (Coral) are bundled in the image. You can use your own models with volume mounts:
+- CPU Model: `/cpu_model.tflite`
+- EdgeTPU Model: `/edgetpu_model.tflite`
+- Labels: `/labelmap.txt`
+
 Run the container with
 ```bash
 docker run --rm \
@@ -26,7 +36,7 @@ docker run --rm \
 -v /etc/localtime:/etc/localtime:ro \
 -p 5000:5000 \
 -e FRIGATE_RTSP_PASSWORD='password' \
-blakeblackshear/frigate:stable
+frigate:latest
 ```
 
 Example docker-compose:
@@ -36,7 +46,7 @@ Example docker-compose:
     restart: unless-stopped
     privileged: true
     shm_size: '1g' # should work for 5-7 cameras
-    image: blakeblackshear/frigate:stable
+    image: frigate:latest
     volumes:
       - /dev/bus/usb:/dev/bus/usb
       - /etc/localtime:/etc/localtime:ro
@@ -117,11 +127,6 @@ sensor:
         value_template: '{{ states.sensor.frigate_debug.attributes["coral"]["inference_speed"] }}' 
         unit_of_measurement: 'ms'
 ```
-## Using a custom model
-Models for both CPU and EdgeTPU (Coral) are bundled in the image. You can use your own models with volume mounts:
-- CPU Model: `/cpu_model.tflite`
-- EdgeTPU Model: `/edgetpu_model.tflite`
-- Labels: `/labelmap.txt`
 
 ## Tips
 - Lower the framerate of the video feed on the camera to reduce the CPU usage for capturing the feed

benchmark.py

@@ -1,79 +1,18 @@
-import os
+import statistics
-from statistics import mean
-import multiprocessing as mp
 import numpy as np
-import datetime
+import time
-from frigate.edgetpu import ObjectDetector, EdgeTPUProcess, RemoteObjectDetector, load_labels
+from frigate.edgetpu import ObjectDetector
 
-my_frame = np.expand_dims(np.full((300,300,3), 1, np.uint8), axis=0)
+object_detector = ObjectDetector()
-labels = load_labels('/labelmap.txt')
 
-######
+frame = np.zeros((300,300,3), np.uint8)
-# Minimal same process runner
+input_frame = np.expand_dims(frame, axis=0)
-######
-# object_detector = ObjectDetector()
-# tensor_input = np.expand_dims(np.full((300,300,3), 0, np.uint8), axis=0)
 
-# start = datetime.datetime.now().timestamp()
+detection_times = []
 
-# frame_times = []
+for x in range(0, 100):
-# for x in range(0, 1000):
+    start = time.monotonic()
-#   start_frame = datetime.datetime.now().timestamp()
+    object_detector.detect_raw(input_frame)
+    detection_times.append(time.monotonic()-start)
 
-#   tensor_input[:] = my_frame
+print(f"Average inference time: {statistics.mean(detection_times)*1000:.2f}ms")
-#   detections = object_detector.detect_raw(tensor_input)
-#   parsed_detections = []
-#   for d in detections:
-#       if d[1] < 0.4:
-#           break
-#       parsed_detections.append((
-#           labels[int(d[0])],
-#           float(d[1]),
-#           (d[2], d[3], d[4], d[5])
-#       ))
-#   frame_times.append(datetime.datetime.now().timestamp()-start_frame)
-
-# duration = datetime.datetime.now().timestamp()-start
-# print(f"Processed for {duration:.2f} seconds.")
-# print(f"Average frame processing time: {mean(frame_times)*1000:.2f}ms")
-
-######
-# Separate process runner
-######
-def start(id, num_detections, detection_queue):
-  object_detector = RemoteObjectDetector(str(id), '/labelmap.txt', detection_queue)
-  start = datetime.datetime.now().timestamp()
-
-  frame_times = []
-  for x in range(0, num_detections):
-    start_frame = datetime.datetime.now().timestamp()
-    detections = object_detector.detect(my_frame)
-    frame_times.append(datetime.datetime.now().timestamp()-start_frame)
-
-  duration = datetime.datetime.now().timestamp()-start
-  print(f"{id} - Processed for {duration:.2f} seconds.")
-  print(f"{id} - Average frame processing time: {mean(frame_times)*1000:.2f}ms")
-
-edgetpu_process = EdgeTPUProcess()
-
-# start(1, 1000, edgetpu_process.detect_lock, edgetpu_process.detect_ready, edgetpu_process.frame_ready)
-
-####
-# Multiple camera processes
-####
-camera_processes = []
-for x in range(0, 10):
-  camera_process = mp.Process(target=start, args=(x, 100, edgetpu_process.detection_queue))
-  camera_process.daemon = True
-  camera_processes.append(camera_process)
-
-start = datetime.datetime.now().timestamp()
-
-for p in camera_processes:
-  p.start()
-
-for p in camera_processes:
-  p.join()
-
-duration = datetime.datetime.now().timestamp()-start
-print(f"Total - Processed for {duration:.2f} seconds.")

config/config.example.yml

@@ -3,13 +3,9 @@ web_port: 5000
 mqtt:
   host: mqtt.server.com
   topic_prefix: frigate
-  # client_id: frigate # Optional -- set to override default client id of 'frigate' if running multiple instances
+#  client_id: frigate # Optional -- set to override default client id of 'frigate' if running multiple instances
-  # user: username # Optional
+#  user: username # Optional -- Uncomment for use
-  #################
+#  password: password # Optional -- Uncomment for use
-  ## Environment variables that begin with 'FRIGATE_' may be referenced in {}.
-  ##   password: '{FRIGATE_MQTT_PASSWORD}'
-  #################
-  # password: password # Optional
 
 #################
 # Default ffmpeg args. Optional and can be overwritten per camera.

detect_objects.py

@@ -1,4 +1,3 @@
-import os
 import cv2
 import time
 import datetime
@@ -9,7 +8,7 @@ import multiprocessing as mp
 import subprocess as sp
 import numpy as np
 import logging
-from flask import Flask, Response, make_response, jsonify, request
+from flask import Flask, Response, make_response, jsonify
 import paho.mqtt.client as mqtt
 
 from frigate.video import track_camera
@@ -17,8 +16,6 @@ from frigate.object_processing import TrackedObjectProcessor
 from frigate.util import EventsPerSecond
 from frigate.edgetpu import EdgeTPUProcess
 
-FRIGATE_VARS = {k: v for k, v in os.environ.items() if k.startswith('FRIGATE_')}
-
 with open('/config/config.yml') as f:
     CONFIG = yaml.safe_load(f)
 
@@ -27,8 +24,6 @@ MQTT_PORT = CONFIG.get('mqtt', {}).get('port', 1883)
 MQTT_TOPIC_PREFIX = CONFIG.get('mqtt', {}).get('topic_prefix', 'frigate')
 MQTT_USER = CONFIG.get('mqtt', {}).get('user')
 MQTT_PASS = CONFIG.get('mqtt', {}).get('password')
-if not MQTT_PASS is None:
-    MQTT_PASS = MQTT_PASS.format(**FRIGATE_VARS)
 MQTT_CLIENT_ID = CONFIG.get('mqtt', {}).get('client_id', 'frigate')
 
 # Set the default FFmpeg config
@@ -73,21 +68,27 @@ class CameraWatchdog(threading.Thread):
             # wait a bit before checking
             time.sleep(30)
 
-            if (self.tflite_process.detection_start.value > 0.0 and 
-                datetime.datetime.now().timestamp() - self.tflite_process.detection_start.value > 10):
-                print("Detection appears to be stuck. Restarting detection process")
-                self.tflite_process.start_or_restart()
-                time.sleep(30)
-
             for name, camera_process in self.camera_processes.items():
                 process = camera_process['process']
+                if (not self.object_processor.get_current_frame_time(name) is None and 
+                    (datetime.datetime.now().timestamp() - self.object_processor.get_current_frame_time(name)) > 30):
+                    print(f"Last frame for {name} is more than 30 seconds old...")
+                    if process.is_alive():
+                        process.terminate()
+                        print("Waiting for process to exit gracefully...")
+                        process.join(timeout=30)
+                        if process.exitcode is None:
+                            print("Process didnt exit. Force killing...")
+                            process.kill()
+                            process.join()
                 if not process.is_alive():
                     print(f"Process for {name} is not alive. Starting again...")
                     camera_process['fps'].value = float(self.config[name]['fps'])
                     camera_process['skipped_fps'].value = 0.0
                     camera_process['detection_fps'].value = 0.0
+                    self.object_processor.camera_data[name]['current_frame_time'] = None
                     process = mp.Process(target=track_camera, args=(name, self.config[name], FFMPEG_DEFAULT_CONFIG, GLOBAL_OBJECT_CONFIG, 
-                        self.tflite_process.detection_queue, self.tracked_objects_queue, 
+                        self.tflite_process.detect_lock, self.tflite_process.detect_ready, self.tflite_process.frame_ready, self.tracked_objects_queue, 
                         camera_process['fps'], camera_process['skipped_fps'], camera_process['detection_fps']))
                     process.daemon = True
                     camera_process['process'] = process
@@ -149,7 +150,7 @@ def main():
             'detection_fps': mp.Value('d', 0.0)
         }
         camera_process = mp.Process(target=track_camera, args=(name, config, FFMPEG_DEFAULT_CONFIG, GLOBAL_OBJECT_CONFIG, 
-            tflite_process.detection_queue, tracked_objects_queue, 
+            tflite_process.detect_lock, tflite_process.detect_ready, tflite_process.frame_ready, tracked_objects_queue, 
             camera_processes[name]['fps'], camera_processes[name]['skipped_fps'], camera_processes[name]['detection_fps']))
         camera_process.daemon = True
         camera_processes[name]['process'] = camera_process
@@ -183,16 +184,14 @@ def main():
         for name, camera_stats in camera_processes.items():
             total_detection_fps += camera_stats['detection_fps'].value
             stats[name] = {
-                'fps': round(camera_stats['fps'].value, 2),
+                'fps': camera_stats['fps'].value,
-                'skipped_fps': round(camera_stats['skipped_fps'].value, 2),
+                'skipped_fps': camera_stats['skipped_fps'].value,
-                'detection_fps': round(camera_stats['detection_fps'].value, 2)
+                'detection_fps': camera_stats['detection_fps'].value
             }
         
         stats['coral'] = {
-            'fps': round(total_detection_fps, 2),
+            'fps': total_detection_fps,
-            'inference_speed': round(tflite_process.avg_inference_speed.value*1000, 2),
+            'inference_speed': round(tflite_process.avg_inference_speed.value*1000, 2)
-            'detection_queue': tflite_process.detection_queue.qsize(),
-            'detection_start': tflite_process.detection_start.value
         }
 
         rc = plasma_process.poll()
@@ -218,26 +217,21 @@ def main():
 
     @app.route('/<camera_name>')
     def mjpeg_feed(camera_name):
-        fps = int(request.args.get('fps', '3'))
-        height = int(request.args.get('h', '360'))
         if camera_name in CONFIG['cameras']:
             # return a multipart response
-            return Response(imagestream(camera_name, fps, height),
+            return Response(imagestream(camera_name),
                             mimetype='multipart/x-mixed-replace; boundary=frame')
         else:
             return "Camera named {} not found".format(camera_name), 404
 
-    def imagestream(camera_name, fps, height):
+    def imagestream(camera_name):
         while True:
-            # max out at specified FPS
+            # max out at 1 FPS
-            time.sleep(1/fps)
+            time.sleep(1)
             frame = object_processor.get_current_frame(camera_name)
             if frame is None:
-                frame = np.zeros((height,int(height*16/9),3), np.uint8)
+                frame = np.zeros((720,1280,3), np.uint8)
-
-            frame = cv2.resize(frame, dsize=(int(height*16/9), height), interpolation=cv2.INTER_LINEAR)
             frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
-
             ret, jpg = cv2.imencode('.jpg', frame)
             yield (b'--frame\r\n'
                 b'Content-Type: image/jpeg\r\n\r\n' + jpg.tobytes() + b'\r\n\r\n')

frigate/edgetpu.py

@@ -1,10 +1,8 @@
 import os
 import datetime
-import hashlib
 import multiprocessing as mp
 import numpy as np
 import SharedArray as sa
-import pyarrow.plasma as plasma
 import tflite_runtime.interpreter as tflite
 from tflite_runtime.interpreter import load_delegate
 from frigate.util import EventsPerSecond
@@ -62,81 +60,77 @@ class ObjectDetector():
         
         return detections
 
-def run_detector(detection_queue, avg_speed, start):
-    print(f"Starting detection process: {os.getpid()}")
-    plasma_client = plasma.connect("/tmp/plasma")
-    object_detector = ObjectDetector()
-
-    while True:
-        object_id_str = detection_queue.get()
-        object_id_hash = hashlib.sha1(str.encode(object_id_str))
-        object_id = plasma.ObjectID(object_id_hash.digest())
-        object_id_out = plasma.ObjectID(hashlib.sha1(str.encode(f"out-{object_id_str}")).digest())
-        input_frame = plasma_client.get(object_id, timeout_ms=0)
-
-        if input_frame is plasma.ObjectNotAvailable:
-            continue
-
-        # detect and put the output in the plasma store
-        start.value = datetime.datetime.now().timestamp()
-        plasma_client.put(object_detector.detect_raw(input_frame), object_id_out)
-        duration = datetime.datetime.now().timestamp()-start.value
-        start.value = 0.0
-
-        avg_speed.value = (avg_speed.value*9 + duration)/10
-        
 class EdgeTPUProcess():
     def __init__(self):
-        self.detection_queue = mp.Queue()
+        # TODO: see if we can use the plasma store with a queue and maintain the same speeds
-        self.avg_inference_speed = mp.Value('d', 0.01)
+        try:
-        self.detection_start = mp.Value('d', 0.0)
+            sa.delete("frame")
-        self.detect_process = None
+        except:
-        self.start_or_restart()
+            pass
+        try:
+            sa.delete("detections")
+        except:
+            pass
 
-    def start_or_restart(self):
+        self.input_frame = sa.create("frame", shape=(1,300,300,3), dtype=np.uint8)
-        self.detection_start.value = 0.0
+        self.detections = sa.create("detections", shape=(20,6), dtype=np.float32)
-        if (not self.detect_process is None) and self.detect_process.is_alive():
+
-            self.detect_process.terminate()
+        self.detect_lock = mp.Lock()
-            print("Waiting for detection process to exit gracefully...")
+        self.detect_ready = mp.Event()
-            self.detect_process.join(timeout=30)
+        self.frame_ready = mp.Event()
-            if self.detect_process.exitcode is None:
+        self.avg_inference_speed = mp.Value('d', 0.01)
-                print("Detection process didnt exit. Force killing...")
+
-                self.detect_process.kill()
+        def run_detector(detect_ready, frame_ready, avg_speed):
-                self.detect_process.join()
+            print(f"Starting detection process: {os.getpid()}")
-        self.detect_process = mp.Process(target=run_detector, args=(self.detection_queue, self.avg_inference_speed, self.detection_start))
+            object_detector = ObjectDetector()
+            input_frame = sa.attach("frame")
+            detections = sa.attach("detections")
+
+            while True:
+                # wait until a frame is ready
+                frame_ready.wait()
+                start = datetime.datetime.now().timestamp()
+                # signal that the process is busy
+                frame_ready.clear()
+                detections[:] = object_detector.detect_raw(input_frame)
+                # signal that the process is ready to detect
+                detect_ready.set()
+                duration = datetime.datetime.now().timestamp()-start
+                avg_speed.value = (avg_speed.value*9 + duration)/10
+
+        self.detect_process = mp.Process(target=run_detector, args=(self.detect_ready, self.frame_ready, self.avg_inference_speed))
         self.detect_process.daemon = True
         self.detect_process.start()
 
 class RemoteObjectDetector():
-    def __init__(self, name, labels, detection_queue):
+    def __init__(self, labels, detect_lock, detect_ready, frame_ready):
         self.labels = load_labels(labels)
-        self.name = name
+
+        self.input_frame = sa.attach("frame")
+        self.detections = sa.attach("detections")
+
         self.fps = EventsPerSecond()
-        self.plasma_client = plasma.connect("/tmp/plasma")
+
-        self.detection_queue = detection_queue
+        self.detect_lock = detect_lock
+        self.detect_ready = detect_ready
+        self.frame_ready = frame_ready
     
     def detect(self, tensor_input, threshold=.4):
         detections = []
-
+        with self.detect_lock:
-        now = f"{self.name}-{str(datetime.datetime.now().timestamp())}"
+            self.input_frame[:] = tensor_input
-        object_id_frame = plasma.ObjectID(hashlib.sha1(str.encode(now)).digest())
+            # unset detections and signal that a frame is ready
-        object_id_detections = plasma.ObjectID(hashlib.sha1(str.encode(f"out-{now}")).digest())
+            self.detect_ready.clear()
-        self.plasma_client.put(tensor_input, object_id_frame)
+            self.frame_ready.set()
-        self.detection_queue.put(now)
+            # wait until the detection process is finished,
-        raw_detections = self.plasma_client.get(object_id_detections, timeout_ms=10000)
+            self.detect_ready.wait()
-
+            for d in self.detections:
-        if raw_detections is plasma.ObjectNotAvailable:
+                if d[1] < threshold:
-            self.plasma_client.delete([object_id_frame])
+                    break
-            return detections
+                detections.append((
-
+                    self.labels[int(d[0])],
-        for d in raw_detections:
+                    float(d[1]),
-            if d[1] < threshold:
+                    (d[2], d[3], d[4], d[5])
-                break
+                ))
-            detections.append((
-                self.labels[int(d[0])],
-                float(d[1]),
-                (d[2], d[3], d[4], d[5])
-            ))
-        self.plasma_client.delete([object_id_frame, object_id_detections])
         self.fps.update()
         return detections

frigate/object_processing.py

@@ -34,6 +34,7 @@ class TrackedObjectProcessor(threading.Thread):
             'best_objects': {},
             'object_status': defaultdict(lambda: defaultdict(lambda: 'OFF')),
             'tracked_objects': {},
+            'current_frame_time': None,
             'current_frame': np.zeros((720,1280,3), np.uint8),
             'object_id': None
         })
@@ -47,6 +48,9 @@ class TrackedObjectProcessor(threading.Thread):
     def get_current_frame(self, camera):
         return self.camera_data[camera]['current_frame']
     
+    def get_current_frame_time(self, camera):
+        return self.camera_data[camera]['current_frame_time']
+
     def run(self):
         while True:
             camera, frame_time, tracked_objects = self.tracked_objects_queue.get()
@@ -89,6 +93,7 @@ class TrackedObjectProcessor(threading.Thread):
                 # Set the current frame as ready
                 ###
                 self.camera_data[camera]['current_frame'] = current_frame
+                self.camera_data[camera]['current_frame_time'] = frame_time
 
                 # store the object id, so you can delete it at the next loop
                 previous_object_id = self.camera_data[camera]['object_id']

frigate/video.py

@@ -98,23 +98,7 @@ def create_tensor_input(frame, region):
     # Expand dimensions since the model expects images to have shape: [1, 300, 300, 3]
     return np.expand_dims(cropped_frame, axis=0)
 
-def start_or_restart_ffmpeg(ffmpeg_cmd, frame_size, ffmpeg_process=None):
+def track_camera(name, config, ffmpeg_global_config, global_objects_config, detect_lock, detect_ready, frame_ready, detected_objects_queue, fps, skipped_fps, detection_fps):
-    if not ffmpeg_process is None:
-        print("Terminating the existing ffmpeg process...")
-        ffmpeg_process.terminate()
-        try:
-            print("Waiting for ffmpeg to exit gracefully...")
-            ffmpeg_process.wait(timeout=30)
-        except sp.TimeoutExpired:
-            print("FFmpeg didnt exit. Force killing...")
-            ffmpeg_process.kill()
-            ffmpeg_process.wait()
-
-    print("Creating ffmpeg process...")
-    print(" ".join(ffmpeg_cmd))
-    return sp.Popen(ffmpeg_cmd, stdout = sp.PIPE, bufsize=frame_size*10)
-
-def track_camera(name, config, ffmpeg_global_config, global_objects_config, detection_queue, detected_objects_queue, fps, skipped_fps, detection_fps):
     print(f"Starting process for {name}: {os.getpid()}")
 
     # Merge the ffmpeg config with the global config
@@ -124,13 +108,6 @@ def track_camera(name, config, ffmpeg_global_config, global_objects_config, dete
     ffmpeg_hwaccel_args = ffmpeg.get('hwaccel_args', ffmpeg_global_config['hwaccel_args'])
     ffmpeg_input_args = ffmpeg.get('input_args', ffmpeg_global_config['input_args'])
     ffmpeg_output_args = ffmpeg.get('output_args', ffmpeg_global_config['output_args'])
-    ffmpeg_cmd = (['ffmpeg'] +
-            ffmpeg_global_args +
-            ffmpeg_hwaccel_args +
-            ffmpeg_input_args +
-            ['-i', ffmpeg_input] +
-            ffmpeg_output_args +
-            ['pipe:'])
 
     # Merge the tracked object config with the global config
     camera_objects_config = config.get('objects', {})    
@@ -172,11 +149,21 @@ def track_camera(name, config, ffmpeg_global_config, global_objects_config, dete
         mask[:] = 255
 
     motion_detector = MotionDetector(frame_shape, mask, resize_factor=6)
-    object_detector = RemoteObjectDetector(name, '/labelmap.txt', detection_queue)
+    object_detector = RemoteObjectDetector('/labelmap.txt', detect_lock, detect_ready, frame_ready)
 
     object_tracker = ObjectTracker(10)
 
-    ffmpeg_process = start_or_restart_ffmpeg(ffmpeg_cmd, frame_size)
+    ffmpeg_cmd = (['ffmpeg'] +
+            ffmpeg_global_args +
+            ffmpeg_hwaccel_args +
+            ffmpeg_input_args +
+            ['-i', ffmpeg_input] +
+            ffmpeg_output_args +
+            ['pipe:'])
+
+    print(" ".join(ffmpeg_cmd))
+    
+    ffmpeg_process = sp.Popen(ffmpeg_cmd, stdout = sp.PIPE, bufsize=frame_size)
     
     plasma_client = plasma.connect("/tmp/plasma")
     frame_num = 0
@@ -193,14 +180,7 @@ def track_camera(name, config, ffmpeg_global_config, global_objects_config, dete
         avg_wait = (avg_wait*99+duration)/100
 
         if not frame_bytes:
-            rc = ffmpeg_process.poll()
+            break
-            if rc is not None:
-                print(f"{name}: ffmpeg_process exited unexpectedly with {rc}")
-                ffmpeg_process = start_or_restart_ffmpeg(ffmpeg_cmd, frame_size, ffmpeg_process)
-                time.sleep(10)
-            else:
-                print(f"{name}: ffmpeg_process is still running but didnt return any bytes")
-            continue
 
         # limit frame rate
         frame_num += 1
@@ -373,5 +353,3 @@ def track_camera(name, config, ffmpeg_global_config, global_objects_config, dete
         plasma_client.put(frame, plasma.ObjectID(object_id))
         # add to the queue
         detected_objects_queue.put((name, frame_time, object_tracker.tracked_objects))
-
-    print(f"{name}: exiting subprocess")