Question about Fpn-SSD-MobileNet-v2 Postprocess

显示  仅  | 搜索替代 

Question about Fpn-SSD-MobileNet-v2 Postprocess

1,372 次查看
Contributor I

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.

标签 (1)
0 项奖励
1 回复

1,169 次查看
NXP Employee
NXP Employee

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?

0 项奖励