Softmax layer output won't sum to 1 in VGG16-SSD

Autonomous Machines Jetson & Embedded Systems Jetson TX2
#1

Hi, AastaLLL,

I'm currently working on TensorRT 3.0 accelerating of VGG16-SSD. I compare every output of each layer with that of caffe version of VGG16-SSD (by comparing firt 100 output of the layer outputdata) and all is OK before Softmax layer. The output of Softmax is wrong, as even it can't sum up to 1 of the 21 float values. I guess it may be some thing wrong with the reshape plugin layer mbox_conf_reshape layer, which is right before the Softmax, but problem still whatever layer output shape i adjust. I debug for two days and read the caffe softmax cpp/cu code agin but find nothing to help. Can ur team give some advices?

Best!
shimiao

#2

Sorry, I find the point. That’s because I write the wrong shape in “mbox_conf_reshape” Plugin Layer.

Plz close it.

#3

Hi, what did you find wrong in the mbox_conf_reshape layer? I am also stuck with the same problem.

#4

Thanks for the update, jiangshimiao1.

This issue is caused by the incorrect implementation of the mbox_conf_reshape plugin.
Not an issue of TensorRT softmax layer.

#5