- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I have run downloader.py (from model_downloader https://github.com/opencv/open_model_zoo/tree/2018/model_downloader) and I got errors.
python3 downloader.py --name text-detection-0001 -o ./text-detection/
###############|| Start downloading models ||###############
...100%, 83 KB, 809 KB/s, 0 seconds passed ========= text-detection-0001.xml ====> ./text-detection/Retail/object_detection/text/pixel_link_mobilenet_v2/0001/text-detection-0001.xml
###############|| Start downloading weights ||###############
...100%, 83 KB, 845 KB/s, 0 seconds passed ========= text-detection-0001.bin ====> ./text-detection/Retail/object_detection/text/pixel_link_mobilenet_v2/0001/text-detection-0001.bin
###############|| Start downloading topologies in tarballs ||###############
###############|| Post processing ||###############
########## Hash sum of ./text-detection/Retail/object_detection/text/pixel_link_mobilenet_v2/0001/text-detection-0001.xml differs from the target, the topology will be deleted !!! ##########
Traceback (most recent call last):
File "downloader.py", line 237, in <module>
compare_hash(top['model_hash'], path_to_model)
File "downloader.py", line 35, in compare_hash
shutil.rmtree(os.path.dirname(path_to_file))
File "/usr/lib/python3.5/shutil.py", line 478, in rmtree
onerror(os.rmdir, path, sys.exc_info())
File "/usr/lib/python3.5/shutil.py", line 476, in rmtree
os.rmdir(path)
OSError: [Errno 39] Directory not empty: './text-detection/Retail/object_detection/text/pixel_link_mobilenet_v2/0001'
________________________
OS: Ubuntu 16.08 (and Ubuntu 18.04 on VirtualBox)
Link Copied
2 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Pardon me Sergey but text-detection-0001 is not one of the topologies available. In fact, when I try your command, I get No such topology: "text-detection-0001"
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
not sure if it helps but JFTR there is a text detection IR in the R5 SDK under
computer_vision_sdk_2018.5.445/deployment_tools/intel_models/text-detection-0001/FP16/text-detection-0001.xml
computer_vision_sdk_2018.5.445/deployment_tools/intel_models/text-detection-0001/FP32/text-detection-0001.xml

Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page