- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Please tell me Nice to meet you, I am learning the OpenVINO program.
Location recognition Python * I get an error in the demo execution program.
Below are the executable programs and error details.
Would you please let me know if you understand the cause of the error?
environment:
OS Ubuntu 18.04
OPENVINO version: openvino_toolkit_p_2021.3.394
Program execution:
: ~ / Open_model_zoo / demos / place_recognition_demo / python
$ python3 place_recognition_demo.py -i / dev / video0 -m ~ / open_model_zoo / tools / downloader / intel / vehicle-detection-0200 / FP16 / vehicle-detection-0200.xml -d CPU -u UTILIZATION_MONITORS -gf ~ / Pictures / GALLERY_FOLDER
error contents:
File "place_recognition_demo.py", line 33, in <module> from images_capture import open_images_capture
ModuleNotFoundError: No module named'image_capture'
* A photo is attached.
Thanking you in advance.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello @s_taneda,
I would recommend you to review Place Recognition Python\* Demo readme for details on how to run this demo.
From you snipped I see that wrong model used, this demo work with Open Model Zoo Pre-Trained netvlad-tf model. You may download and convert this model to OpenVINO IR using Open Model Zoo Model Downloader. Each Open Model Zoo demo contain models.lst file, which lists models supported by this demo. This file also can be used as a parameter for Model Downloader, so if you call it like:
python3 <omz_dir>/tools/downloader/downloader.py --list <omz_dir>/demos/place_recognition_demo/python/models.lst
it will download models required for this demo. Note, public models need to be converted to OpenVINO IR before run on OpenVINO Inference Engine, and you may achieve that with following call:
python3 <omz_dir>/tools/downloader/converter.py --list <omz_dir>/demos/place_recognition_demo/python/models.lst
Of course, you will need configure python environment
When you want to use usb camera as an input you need specify camera id (it is a number, usually 0 if you have only one camera connected to system)
Regards,
Vladimir
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi S_Taneda,
This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.
Regards,
Wan

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