allow user to disable/enable speech synthesis

Author: sjentzsch

config/config.obj_detect.sample.yml

@@ -3,6 +3,7 @@
 ## ATTENTION: Do not modify 'config.object_detection.sample.yml' !! You should create a copy named 'config.object_detection.yml' and modify that one !!
 
 
+# see https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md
 model_name: 'ssd_mobilenet_v1_coco_11_06_2017'
 model_dl_base_path: 'http://download.tensorflow.org/models/object_detection/'
 model_dl_file_format: '.tar.gz'
@@ -21,3 +22,6 @@ input_video: 0
 
 # visualize the results of the object detection
 visualizer_enabled: True
+
+# synthesize speech (using Amazon Polly as of now)
+speech_enabled: True

obj_detect.py

@@ -46,7 +46,7 @@
 # ## Download Model
 MODEL_FILE = cfg['model_name'] + cfg['model_dl_file_format']
 if not os.path.isfile(PATH_TO_CKPT):
-  print('Model not found. We will download it now.')
+  print('Model not found. Downloading it now.')
   opener = urllib.request.URLopener()
   opener.retrieve(cfg['model_dl_base_path'] + MODEL_FILE, '../' + MODEL_FILE)
   tar_file = tarfile.open('../' + MODEL_FILE)
@@ -82,7 +82,7 @@
     # TODO: Usually FPS calculation lives in a separate thread. As is now, the interval is a minimum value for each iteration.
     fps = FPS(cfg['fps_interval']).start()
     vis = Visualizer(cfg['visualizer_enabled'])
-    proc = Processor()
+    proc = Processor(cfg['speech_enabled'])
 
     while(input.isActive()):
 #      startTime=datetime.now()

stuff/helper.py

@@ -51,8 +51,8 @@ def fps(self):
 
 
 class Visualizer:
-    def __init__(self, enabled):
-        self._enabled = enabled
+    def __init__(self, visualizer_enabled):
+        self._enabled = visualizer_enabled
         self._windowPlaced = False
         self._screen = display.Display().screen().root.get_geometry()
 
@@ -86,8 +86,10 @@ def cleanup(self):
 
 
 class Processor:
-    def __init__(self):
-        self._speech = SpeechSynthesizer()
+    def __init__(self, speech_enabled):
+        self._speech_enabled = speech_enabled
+        if self._speech_enabled:
+          self._speech = SpeechSynthesizer()
 
     def process(self, boxes, scores, classes, num, image_shape):
 
@@ -115,7 +117,7 @@ def getIndefiniteArticle(word):
             """
             return 'an' if word[:1].lower() in 'aeiou' else 'a'
 
-        if(len(obj) > 0):
+        if(self._speech_enabled and len(obj) > 0):
             self._speech.request("I am " + str(obj[0][1]) + "% certain I see " + getIndefiniteArticle(obj[0][0]) + " " + obj[0][0])
 
     def cleanup(self):