如何将 ssd_mobilenet_v1_COCO_2017_11_17 加载到本地的 object_detection_webcam？

Question

MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90


#Download Model

# you can manually download this
opener = urllib.request.URLopener()
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)

tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
  file_name = os.path.basename(file.name)
  if 'frozen_inference_graph.pb' in file_name:
    tar_file.extract(file, os.getcwd())

This piece of code basically downloads the ssd_mobilenet_v1_COCO_2017_11_17 model each time I run the object_detection_webcam.py.

How can I run the same file without having to download ssd_mobilenet_v1_COCO_2017_11_17 each time I run the script ? I'm very new to working with .tar files.

Your help will be appreciated

Answer 1

Add a check to see if the file already exists and don't download if it does

if not os.path.isfile(MODEL_FILE):
    # Code to download and extract goes here