Wrong tensorrt inference on sampleSSDUFF


I have used sampleSSDUFF.cpp to run inference on ssd inception 2017 model.

It worked perfectly.

Then I retrained my model with pet dataset with 37 classes.
I got good results in tensorflow. I tetsed it.
bounding box is also correct.

I used tensorflow 1.14.0
object detection api from november 17 2017.

Everything is correct for now

But when I port it ot Uff, I get 795 nodes.
then when I use that uff insampleSSDUFF.cpp.

I get wrong detections.

I get something like :

Image name:/english_cocker_spaniel_24.jpg, Label: Abyssinian, confidence: 93% xmin: 0 ymin: 8500 xmax: 4.48887 ymax: 27.7736

Bounding box and label info is not correct.

I get results as english_cocker_spaniel_24_inferenced .

But it works well with standard ssd ncpetion 2017-11-17 model for 91 classes.

What could be the problem???
Please let me know the problem.

Script I am using works perfectly for standard model but not for custom trained model.
I have 37 classes.
I gave 38 in the config script

Hi @god_ra. I get the same problem. The boudingbox is wrong with uff model but OK with .pb file. Did you already fix it when get uff model?

Refer this,
it could be the reason.

hi @god_ra. Thank you!