- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
According to the note on this page Faster RCNN and Mask RCNN models are only supported on GPU and CPU: https://software.intel.com/en-us/articles/OpenVINO-Using-TensorFlow
However, in the release notes for 2019 R1 Known Issue #36 says "TensorFlow faster-rcnn-inception-v2 accuracy is lower than CPU reference (3.7% of relative difference) on Intel® Movidius™ Neural Compute Stick, Intel® Neural Compute Stick 2 and Intel® Vision Accelerator Design with Intel® Movidius™ VPUs"
Do Faster RCNN IRs now run on MYRIAD / NCS? (even if they have slightly lower accuracy...)
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear Mike:
In the latest 2019 R1 document below it is mentioned that faster_rcnn_inception_v2, faster_rcnn_resnet101 is definitely supported on MYRIAD:
https://docs.openvinotoolkit.org/latest/_docs_IE_DG_supported_plugins_MYRIAD.html
Thanks,
Shubha
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear Mike:
In the latest 2019 R1 document below it is mentioned that faster_rcnn_inception_v2, faster_rcnn_resnet101 is definitely supported on MYRIAD:
https://docs.openvinotoolkit.org/latest/_docs_IE_DG_supported_plugins_MYRIAD.html
Thanks,
Shubha
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Great news, Thanks!
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page