For a project I want to build an application for the PX 2 using an own neural network.
The network is fed with two images and they are both dwImageCuda.
My problem is that how to initialize my network with two dwImageCuda as the input of network.
The sample “sample_object_detect” only provides the sample with one image as input.
Thank you very much for your help, SteveNV. I succeeded to write the code for multiple images as input.
But, a new problem occurred when I transfered my own Caffe model to the TensorRT model.
LSTM modules are added in my model and it failed when I used the driveworks API to generate TensorRT model.
The error is like:
Error parsing text-format ditcaffe.NetParameter: 15:19: Message type “ditcaffe.LayerParameter” has no field named “recurrent_param”.)
It seems like TensorRT can not parse the LSTM layer in Caffe model. However, in TensorRT developer guide, I find that the LSTM layer is supported by tensorRT4.
The version of driveworks on my ubuntu16.04 is 1.2.
Please let me know if you need any other info.