PyTorch and TorchVision FasterRCNN interpreting the output in C++ GenericDict - c++

Question

I'm trying to interpret the output of FasterRCNN in C++ and I'm fighting with the GenericDict type.
My code is as follows:
#include <opencv4/opencv2/opencv.hpp>
#include <opencv4/opencv2/shape.hpp>
#include <opencv4/opencv2/imgcodecs.hpp>
#include <opencv4/opencv2/highgui.hpp>
#include <opencv4/opencv2/imgproc.hpp>
#include <opencv4/opencv2/core/utility.hpp>
#include <opencv4/opencv2/core/mat.hpp>
#include <c10/cuda/CUDAStream.h>
#include <torch/csrc/autograd/grad_mode.h>
#include <torch/csrc/api/include/torch/torch.h>
#include <torch/script.h>
#include <torchvision/vision.h>
#include <torchvision/nms.h>
#include <iostream>
#include <memory>
#include <string>
int main(int argc, const char* argv[])
{
if (argc != 3)
{
printf("usage: %s <path-to-exported-script-module> <image_to_test>\n",argv[0]);
return -1;
}
std::string module_filename = argv[1];
std::string image_file = argv[2];
try
{
cv::Mat input_img = cv::imread(image_file, cv::IMREAD_GRAYSCALE);
torch::autograd::AutoGradMode guard(false);
// Deserialize the ScriptModule from a file using torch::jit::load().
torch::jit::script::Module module = torch::jit::load(module_filename);
assert(module.buffers().size() > 0);
module.eval();
// Assume that the entire model is on the same device.
// We just put input to this device.
auto device = (*std::begin(module.buffers())).device();
const int height = input_img.rows;
const int width = input_img.cols;
const int channels = 1;
auto input = torch::from_blob(input_img.data, {height, width, channels}, torch::kUInt8);
// HWC to CHW
// input = input.to(device, torch::kFloat).permute({2, 0, 1}).contiguous();
input = input.to(device, torch::kFloat).permute({2, 0, 1}).contiguous();
// run the network
std::vector<at::Tensor> inputs;
inputs.push_back(input);
auto output = module.forward({inputs});
if (device.is_cuda())
c10::cuda::getCurrentCUDAStream().synchronize();
std::cout << "output: " << output << std::endl;
auto outputs = output.toTuple()->elements();
std::cout << "outputs: " << outputs << std::endl;
for( auto& elem : outputs )
{
std::cout << "elem: " << elem << std::endl;
if( elem.isGenericDict() )
{
std::cout << "elem is generic dict: " << elem << std::endl;
c10::Dict<c10::IValue, c10::IValue> dict = elem.toGenericDict();
auto elem_vector_0 = dict.at(c10::IValue("scores")).toIntVector();
auto elem_vector_1 = dict.at(c10::IValue("boxes")).toIntVector();
auto elem_vector_2 = dict.at(c10::IValue("labels")).toIntVector();
for( auto& ee0 : elem_vector_0 )
{
std::cout << "elem_vector_0" << ee0 << std::endl;
}
for( auto& ee0 : elem_vector_1 )
{
std::cout << "elem_vector_1" << ee0 << std::endl;
}
for( auto& ee0 : elem_vector_2 )
{
std::cout << "elem_vector_2" << ee0 << std::endl;
}
}
}
cv::namedWindow("Display Image", cv::WINDOW_AUTOSIZE );
cv::imshow("Display Image", input_img);
cv::waitKey(0);
}
catch(const c10::Error& e)
{
std::cerr << e.what() << std::endl;
return -1;
}
catch(const cv::Exception& e)
{
std::cerr << e.what() << std::endl;
return -1;
}
catch(const std::exception& e)
{
std::cerr << e.what() << std::endl;
return -1;
}
catch(...)
{
std::cerr << "Unknown error" << std::endl;
return -1;
}
std::cout << "ok\n";
return 0;
}
and the output is:
(base) fstrati#fstrati-desktop:~/libtorch_shared_cuda_10.1/load_and_run_model/Release$ ./load_and_run_model ./torch_script_v0.2.pt test_img.png
[W faster_rcnn.py:95] Warning: RCNN always returns a (Losses, Detections) tuple in scripting (function )
output: ({}, [{boxes: [ CPUFloatType{0,4} ], labels: [ CPULongType{0} ], scores: [ CPUFloatType{0} ]}])
outputs: {} [{boxes: [ CPUFloatType{0,4} ], labels: [ CPULongType{0} ], scores: [ CPUFloatType{0} ]}]
elem: {}
elem is generic dict: {}
Argument passed to at() was not in the map.
I'm struggling to find a way to extract the boxes, labels and scores from the dictionary
GenericDict.
This map is strange, I cannot iterate on it and I cannot access first and second types...
with it->first it->second
Any ideas ?
Thanks in advance

Answer 1

I think the following method can resolve the main problem here,
output = module.forward(inputs);
auto detections = output.toTuple()->elements().at(1).toList().get(0).toGenericDict();
std::cout << ">>> detections labels: " << detections.at("labels") << std::endl;
std::cout << ">>> detections boxes: " << detections.at("boxes") << std::endl;
std::cout << ">>> detections scores: " << detections.at("scores") << std::endl;
Besides, I've added an executable file https://github.com/zhiqwang/yolov5-rt-stack/tree/master/deployment/libtorch to show how libtorch works.