Clean up of code.

Author: datitran

README.md

@@ -4,16 +4,22 @@ A real-time object recognition application using [Google's TensorFlow Object Det
 
 ## Getting Started
 1. `conda env create -f environment.yml`
-2. `python object_detection_app.py`
+2. `python object_detection_app.py` 
+ Optional arguments (default value):
+ * Device index of the camera `--source=0`
+ * Width of the frames in the video stream `--width=480`
+ * Height of the frames in the video stream `--height=360`
+ * Number of workers `--num-workers=2`
+ * Size of the queue `--queue-size=5`
 
 ## Requirements
 - [Anaconda / Python 3.5](https://www.continuum.io/downloads)
 - [TensorFlow 1.2](https://www.tensorflow.org/)
-- [OpenCV 3.1](http://opencv.org/)
+- [OpenCV 3.0](http://opencv.org/)
 
 ## Notes
-- OpenCV might crash on OSX after a while. See open issue and solution [here](https://github.com/opencv/opencv/issues/5874)
-- Moving the `.read()` part of the video stream in a subprocess did not work but only to a separate thread
+- OpenCV 3.1 might crash on OSX after a while, so that's why I had to switch to version 3.0. See open issue and solution [here](https://github.com/opencv/opencv/issues/5874).
+- Moving the `.read()` part of the video stream in a multiple child processes did not work. However, it was possible to move it to a separate thread.
 
 ## Copyright
 

environment.yml

@@ -4,12 +4,11 @@ channels: !!python/tuple
 - defaults
 dependencies:
 - freetype=2.5.5=2
-- hdf5=1.8.17=1
 - jbig=2.1=0
+- jlaura::opencv3=3.0.0=py35_0
 - jpeg=9b=0
 - libpng=1.6.27=0
 - libtiff=4.0.6=3
-- menpo::opencv3=3.1.0=py35_0
 - menpo::tbb=4.3_20141023=0
 - mkl=2017.0.1=0
 - numpy=1.13.0=py35_0

object_detection_app.py

@@ -1,5 +1,6 @@
 import os
 import cv2
+import time
 import argparse
 import multiprocessing
 import numpy as np
@@ -21,9 +22,6 @@
 
 NUM_CLASSES = 90
 
-NUM_WORKERS = 2 # cv2.getNumberOfCPUs() - 1
-QUEUE_SIZE = 5
-
 # Loading label map
 label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
 categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
@@ -88,33 +86,47 @@ def worker(input_q, output_q):
  parser = argparse.ArgumentParser()
  parser.add_argument('-src', '--source', dest='video_source', type=int,
  default=0, help='Device index of the camera.')
+ parser.add_argument('-wd', '--width', dest='width', type=int,
+ default=480, help='Width of the frames in the video stream.')
+ parser.add_argument('-ht', '--height', dest='height', type=int,
+ default=360, help='Height of the frames in the video stream.')
+ parser.add_argument('-num-w', '--num-workers', dest='num_workers', type=int,
+ default=2, help='Number of workers.')
+ parser.add_argument('-q-size', '--queue-size', dest='queue_size', type=int,
+ default=5, help='Size of the queue.')
  args = parser.parse_args()
 
  logger = multiprocessing.log_to_stderr()
  logger.setLevel(multiprocessing.SUBDEBUG)
 
- input_q = Queue(maxsize=QUEUE_SIZE)
- output_q = Queue(maxsize=QUEUE_SIZE)
+ input_q = Queue(maxsize=args.queue_size)
+ output_q = Queue(maxsize=args.queue_size)
 
  process = Process(target=worker, args=((input_q, output_q)))
  process.daemon = True
- pool = Pool(NUM_WORKERS, worker, (input_q, output_q))
+ pool = Pool(args.num_workers, worker, (input_q, output_q))
 
- video_capture = WebcamVideoStream(src=args.video_source).start()
+ video_capture = WebcamVideoStream(src=args.video_source,
+ width=args.width,
+ height=args.height).start()
  fps = FPS().start()
 
  while True: # fps._numFrames < 120
  frame = video_capture.read()
  input_q.put(frame)
 
+ t = time.time()
+
  cv2.imshow('Video', output_q.get())
  fps.update()
 
+ print('[INFO] elapsed time: {:.2f}'.format(time.time() - t))
+
  if cv2.waitKey(1) & 0xFF == ord('q'):
  break
 
  fps.stop()
- print('[INFO] elasped time: {:.2f}'.format(fps.elapsed()))
+ print('[INFO] elapsed time (total): {:.2f}'.format(fps.elapsed()))
  print('[INFO] approx. FPS: {:.2f}'.format(fps.fps()))
 
  video_capture.stop()

utils.py

@@ -38,12 +38,12 @@ def fps(self):
 
 
 class WebcamVideoStream:
- def __init__(self, src=0):
+ def __init__(self, src, width, height):
  # initialize the video camera stream and read the first frame
  # from the stream
  self.stream = cv2.VideoCapture(src)
- self.stream.set(cv2.CAP_PROP_FRAME_WIDTH, 480)
- self.stream.set(cv2.CAP_PROP_FRAME_HEIGHT, 360)
+ self.stream.set(cv2.CAP_PROP_FRAME_WIDTH, width)
+ self.stream.set(cv2.CAP_PROP_FRAME_HEIGHT, height)
  (self.grabbed, self.frame) = self.stream.read()
 
  # initialize the variable used to indicate if the thread should