- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I'm using the Python API, OpenVINO 2020.4 and primarily do development on the NCS2 (-d MYRIAD)
I read a network in from the xml + bin source using functions read_network() and load_network(). Then I export the executable network as a blob file. The xml + bin file is of size A bytes, and the blob is of size B bytes.
I've consistently seen B>A by a significant margin of ~2-3 MB for all models that I've tested from the open model zoo. Is this expected behavior? Is there any way to avoid it?
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Sonebu,
Thanks for reaching out.
Probably no, the size of the blob file should be the same as the XML + bin file.
You can check this page on how to run the MYRIAD compile to get the blob file. Then, you will see the blob file and the XML + bin file should be in the same size.
https://docs.luxonis.com/tutorials/converting_openvino_model/#run-myriad_compile
Regards,
Aznie
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Sonebu,
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,
Aznie
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page