Question about Fpn-SSD-MobileNet-v2 Postprocess
‎09-13-2022
11:04 PM
2,183 Views
June1124
Contributor I
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I trained the object detection model using fpn-ssd-mobilenetv2 inside eIQ and successfully exported it in tflite format, but its output is float32[1,19125,7], I expect the result to be TFLITE_DETECTION_POSTPROCESS, which has the dimensions [1,1,4]. . Is there a solution for this, please? Or how to decode [1,19125,7]?
My eIQ Portal version is 2.5.12.
1 Reply
‎11-16-2022
06:08 AM
1,980 Views

NXP Employee
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello June, why do you expect the result to be TFLITE_DETECTION_POSTPROCESS and where does this variable/macro come from? Can you explain your issue in more detail, please?
