https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Question-about-Fpn-SSD-MobileNet-v2-Postprocess/m-p/1554929#M635 <P>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?</P> Wed, 16 Nov 2022 13:08:15 GMT david_piskula 2022-11-16T13:08:15Z https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Question-about-Fpn-SSD-MobileNet-v2-Postprocess/m-p/1521690#M629 <P>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]?</P><P>My eIQ Portal version is 2.5.12.</P> Wed, 14 Sep 2022 06:04:17 GMT https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Question-about-Fpn-SSD-MobileNet-v2-Postprocess/m-p/1521690#M629 June1124 2022-09-14T06:04:17Z https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Question-about-Fpn-SSD-MobileNet-v2-Postprocess/m-p/1554929#M635 <P>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?</P> Wed, 16 Nov 2022 13:08:15 GMT https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Question-about-Fpn-SSD-MobileNet-v2-Postprocess/m-p/1554929#M635 david_piskula 2022-11-16T13:08:15Z