TensorRT Plugin layer output count is not equal to caffe output count

I have built a SSD net using TensorRT 3.0 in TX2 with some plugin layers such as reshape, permute and so on. While I run the net, it returns error message “Plugin layer output count is not equal to caffe output count” after detectiong_out layer with Warning: “Flatten layer ignored. GIE implicitly flattens input to Fully Connected layers, but in other circumstances this will result in undefined behavior.” I did not add Flatten layer in PluginFactory, and I’m not sure whether it is necessary to add Flatten layer in PluginFactory. And I do not know what caused the result “Plugin layer output count is not equal to caffe output count” and how to solve it. Could someone give me some suggestions? Thank you in advance!

Hi,

We have correct your topic to the Jetson TX2 board.

Our users have met this issue before.
Please check following topic for more information:
https://devtalk.nvidia.com/default/topic/1026215/errors-when-using-tensorrt2-to-accelerate-ssd-caffe-/

Thanks.

Hi fujiaweigege, I am also currently stuck with the same problem. Did you have to implement the Flatten layer on your own to fix the problem?

Hi, marvinreza

Could you check the link mentioned in #2?
Thanks.