I have an acoustic model that successfully converted from ONNX to OpenVino. However, in OpenVino this model outputs tensor that consists of zeroes from some position.
#include <iostream>
#include <fstream>
#include <iterator>
#include <inference_engine.hpp>
typedef struct {
float* data;
size_t size;
size_t timeLen;
} Fbank;
using namespace InferenceEngine;
using std::cout;
using std::endl;
void print_arr(std::string text, const float* arr, int l, int r) {
cout << text << endl;
for (int i = l; i < r; i++) {
cout << arr[i] << " ";
}
cout << endl;
}
void doInference(ExecutableNetwork& executable_network, const std::string& input_name, const std::string& output_name, Fbank* fbank) {
InferRequest infer_request = executable_network.CreateInferRequest();
InferenceEngine::TensorDesc tDesc(InferenceEngine::Precision::FP32,
{fbank->size, fbank->timeLen}, InferenceEngine::Layout::HW);
Blob::Ptr blob = InferenceEngine::make_shared_blob<float>(tDesc, fbank->data);
infer_request.SetBlob(input_name, blob);
infer_request.Infer();
Blob::Ptr output_blob = infer_request.GetBlob(output_name);
auto dims = output_blob->getTensorDesc().getDims();
size_t batchSize = dims[0];
size_t T = dims[1];
size_t D = dims[2];
MemoryBlob::CPtr moutput = as<MemoryBlob>(output_blob);
if (!moutput) {
return;
}
auto moutputHolder = moutput->rmap();
const float *pred = moutputHolder.as<const float*>();
print_arr("AM output:", pred, D*29, D*31);
}
int main() {
Fbank* fbank = new Fbank;
fbank->size = 64;
fbank->timeLen = 2000;
fbank->data = new float[64*2000];
Core ie;
CNNNetwork network = ie.ReadNetwork("quartznet_random.xml", "quartznet_random.bin");
std::string input_name = network.getInputsInfo().begin()->first;
std::string output_name = network.getOutputsInfo().begin()->first;
network.getOutputsInfo().begin()->second->setPrecision(Precision::FP32);
ExecutableNetwork executable_network = ie.LoadNetwork(network, "cpu");
doInference(executable_network, input_name, output_name, fbank);
return 0;
}
Outputs:
AM output:
0.138650 -5.833140 -8.023724 -7.637482 -8.001101 -9.033963 -8.029905 -8.132050 -9.186495 -8.537528 -8.788505 -9.240234 -8.547676 -8.673388 0.000000 0.000000 -0.000000 0.000000 -0.000000 0.000000 0.000000 -0.000000 -0.000000 0.000000 -0.000000 0.000000 0.000000 -0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 -0.000000 0.000000 0.000000 -0.000000 0.000000 0.000000 -0.000000 -0.000000 -0.000000 -0.000000 -0.000000 0.000000 -0.000000 -0.000000 -0.000000 0.000000 -0.000000 -0.000000 -0.000000 0.000000 0.000000 -0.000000 -0.000000 0.000000 -0.000000 0.000000 -0.000000 -0.000000 -0.000000 0.000000 -0.000000 -0.000000 0.000000 -0.000000 0.000000
If I run ONNX model in Python using onnxruntime, the output will be correct. (Example).
Is it possible to fix it?
P.S. Command to convert the model from ONNX: python3 mo_onnx.py —input_model model.onnx —output="output" —input="fbanks[64 2000]"
