#============================
#to generate onnx graph
#============================
import torch
import torch.nn as nn
import torch.nn.init as init
import torch.onnx
import onnxruntime

class TestNet(nn.Module):

    def __init__(self):
        super(TestNet, self).__init__()

    def forward(self, x):
        x = torch.reciprocal(1+torch.exp(x))
        return x

torch_model = TestNet()
#x = torch.randn(1, 1, 2, 2)
x = torch.ones(2, 2)
torch_out = torch_model(x)

# Export the model
torch.onnx.export(torch_model,               # model being run
                  x,                         # model input (or a tuple for multiple inputs)
                  "test.onnx",   # where to save the model (can be a file or file-like object)
                  export_params=True,        # store the trained parameter weights inside the model file
                  opset_version=10,          # the ONNX version to export the model to
                  do_constant_folding=True,  # whether to execute constant folding for optimization
                  input_names = ['input'],   # the model's input names
                  output_names = ['output'], # the model's output names
                  #dynamic_axes={'input' : {0 : 'batch_size'},    # variable length axes
                  #              'output' : {0 : 'batch_size'}}
                  )


ort_session = onnxruntime.InferenceSession("test.onnx")

def to_numpy(tensor):
    return tensor.detach().cpu().numpy() if tensor.requires_grad else tensor.cpu().numpy()

# compute ONNX Runtime output prediction
ort_inputs = {ort_session.get_inputs()[0].name: to_numpy(x)}
ort_outs = ort_session.run(None, ort_inputs)
print(f"x= {to_numpy(x)}" )
print(ort_outs[0])

//====================================================
//to find bugs
//====================================================
#define _CRT_SECURE_NO_WARNINGS
#include <iostream>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>

using namespace cv;
using namespace dnn;
using namespace std;

int main()
{
    Net net = readNet("E:/tmp/opencv_onnx_bug/code/onnx_find/python/test.onnx");


    cv::Mat blob(2 , 2 , CV_32F, Scalar(1));


    net.setInput(blob);

    vector<Mat> outs;
    net.forward(outs, GetOutputsNames(net));//"binary"GetOutputsNames()"shrink"this->net.getUnconnectedOutLayersNames()
    Mat binary = outs[0];
    cv::FileStorage file2("some_name.txt", cv::FileStorage::WRITE);
    file2 << "matName" << binary;
    cout << binary << endl;
    CV_Assert(outs.size() == 1);
}