the result will change every time i run the inference, although the variation is slight, the result is below
the results are defferent between two detectons about image-71.
there is big difference between the 1080ti and jetson tx2,
the confidence about image-71 is much lower, I don't know why.
I tried your code, although your implementation is mobilenet-SSD, seems you have solved this problem? I run many times at 1080ti and they have the same coordinates value, and the result at jetson tx2 has slightly differenence, the results are close to each other.
Could you give me some advices? I would be very grateful.
@Ghustwb I found your question at NVIDIA's forum, here: https://devtalk.nvidia.com/default/topic/1043279/same-tensorrt-code-get-different-result/?offset=10#5307682 I refer to the same github code as you mentioned to build SSD tensorRT version https://github.com/saikumarGadde/tensorrt-ssd-easy And now I came cross the same problem as you raised at nvidia's forum:
I tried your code, although your implementation is mobilenet-SSD, seems you have solved this problem? I run many times at 1080ti and they have the same coordinates value, and the result at jetson tx2 has slightly differenence, the results are close to each other.
Could you give me some advices? I would be very grateful.