- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
how to convert SSD model to IR INT 8 . I don't see INIT8 in --data_type {FP16,FP32,half,float}
file convert : opt/intel/openvino/deployment_tools/model_optimizer/mo.py
Link Copied
1 Reply
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Pham,
You may use DL Workbench to lower the precision of the model from FP32 to INT8 with a process called calibration.
Please refer INT8 Calibration to know the overall flow for converting a model from FP32 to INT8.
Regards,
Jaivin
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