RPROI Failed for different parameters

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

I am getting the below error when I create a RPROI plugin with the following parameters:

constexpr int anchorsRatioCount = 3;
constexpr int anchorsScaleCount = 3;
constexpr int poolingH = 7;
constexpr int poolingW = 7;
constexpr int nmsMaxOut = 50;
constexpr float iouThreshold = 0.7f;
const float anchorsRatios[anchorsRatioCount] = { 0.5f, 1.0f, 2.0f };
const float anchorsScales[anchorsScaleCount] = { 1.0f, 4.0f, 8.0f };
constexpr int featureStride = 16;
constexpr int preNmsTop = 1024;
constexpr float minBoxSize = 1;
constexpr float spatialScale = 0.0625f;

NvPluginFasterRCNN.cu:170: virtual int nvinfer1::plugin::RPROIPlugin::enqueue(int, const void* const*, void**, void*, cudaStream_t): Assertion `status == STATUS_SUCCESS’ failed.
Aborted

Is it a valid set of Input for this plugin?

2

Hello, can you provide details on the platforms you are using?

Linux distro and version
GPU type
nvidia driver version
CUDA version
CUDNN version
Python version [if using python]
Tensorflow version
TensorRT version

Please include the steps/files used to reproduce the problem along with the output of infer_device.

3

Linux Distro - L4T 28.2
GPU type - Tegra TX1
CUDA - 9.0
CUDNN - 7.1.5
TENSORRT - 4.1.3
Not using python and tensorflow

I used the sampleFasterRCNN sample code and modified it to our requirements. I just wanted to know, if the input blob sizes are all correct, then are the above mentioned parameters valid for the RPROI Plugin?

4

have you solved this issue??