Different output from Libtorch C++ and pytorch - c++

Question

I'm using the same traced model in pytorch and libtorch but I'm getting different outputs.
Python Code:
import cv2
import numpy as np
import torch
import torchvision
from torchvision import transforms as trans
# device for pytorch
device = torch.device('cuda:0')
torch.set_default_tensor_type('torch.cuda.FloatTensor')
model = torch.jit.load("traced_facelearner_model_new.pt")
model.eval()
# read the example image used for tracing
image=cv2.imread("videos/example.jpg")
test_transform = trans.Compose([
trans.ToTensor(),
trans.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])
resized_image = cv2.resize(image, (112, 112))
tens = test_transform(resized_image).to(device).unsqueeze(0)
output = model(tens)
print(output)
C++ Code:
#include <iostream>
#include <algorithm>
#include <opencv2/opencv.hpp>
#include <torch/script.h>
int main()
{
try
{
torch::jit::script::Module model = torch::jit::load("traced_facelearner_model_new.pt");
model.to(torch::kCUDA);
model.eval();
cv::Mat visibleFrame = cv::imread("example.jpg");
cv::resize(visibleFrame, visibleFrame, cv::Size(112, 112));
at::Tensor tensor_image = torch::from_blob(visibleFrame.data, { 1, visibleFrame.rows,
visibleFrame.cols, 3 }, at::kByte);
tensor_image = tensor_image.permute({ 0, 3, 1, 2 });
tensor_image = tensor_image.to(at::kFloat);
tensor_image[0][0] = tensor_image[0][0].sub(0.5).div(0.5);
tensor_image[0][1] = tensor_image[0][1].sub(0.5).div(0.5);
tensor_image[0][2] = tensor_image[0][2].sub(0.5).div(0.5);
tensor_image = tensor_image.to(torch::kCUDA);
std::vector<torch::jit::IValue> input;
input.emplace_back(tensor_image);
// Execute the model and turn its output into a tensor.
auto output = model.forward(input).toTensor();
output = output.to(torch::kCPU);
std::cout << "Embds: " << output << std::endl;
std::cout << "Done!\n";
}
catch (std::exception e)
{
std::cout << "exception" << e.what() << std::endl;
}
}
The model gives (1x512) size output tensor as shown below.
Python output
tensor([[-1.6270e+00, -7.8417e-02, -3.4403e-01, -1.5171e+00, -1.3259e+00,
-1.1877e+00, -2.0234e-01, -1.0677e+00, 8.8365e-01, 7.2514e-01,
2.3642e+00, -1.4473e+00, -1.6696e+00, -1.2191e+00, 6.7770e-01,
...
-7.1650e-01, 1.7661e-01]], device=‘cuda:0’,
grad_fn=)
C++ output
Embds: Columns 1 to 8 -84.6285 -14.7203 17.7419 47.0915 31.8170 57.6813 3.6089 -38.0543
Columns 9 to 16 3.3444 -95.5730 90.3788 -10.8355 2.8831 -14.3861 0.8706 -60.7844
...
Columns 505 to 512 36.8830 -31.1061 51.6818 8.2866 1.7214 -2.9263 -37.4330 48.5854
[ CPUFloatType{1,512} ]
Using
Pytorch 1.6.0
Libtorch 1.6.0
Visual studio 2019
Windows 10
Cuda 10.1

Answer 1

before the final normalization, you need to scale your input to the range 0-1 and then carry on the normalization you are doing. convert to float and then divide by 255 should get you there. Here is the snippet I wrote, there might be some syntaax errors, that should be visible.
Try this :
#include <iostream>
#include <algorithm>
#include <opencv2/opencv.hpp>
#include <torch/script.h>
int main()
{
try
{
torch::jit::script::Module model = torch::jit::load("traced_facelearner_model_new.pt");
model.to(torch::kCUDA);
cv::Mat visibleFrame = cv::imread("example.jpg");
cv::resize(visibleFrame, visibleFrame, cv::Size(112, 112));
at::Tensor tensor_image = torch::from_blob(visibleFrame.data, { visibleFrame.rows,
visibleFrame.cols, 3 }, at::kByte);
tensor_image = tensor_image.to(at::kFloat).div(255).unsqueeze(0);
tensor_image = tensor_image.permute({ 0, 3, 1, 2 });
ensor_image.sub_(0.5).div_(0.5);
tensor_image = tensor_image.to(torch::kCUDA);
// Execute the model and turn its output into a tensor.
auto output = model.forward({tensor_image}).toTensor();
output = output.cpu();
std::cout << "Embds: " << output << std::endl;
std::cout << "Done!\n";
}
catch (std::exception e)
{
std::cout << "exception" << e.what() << std::endl;
}
}
I don't have access to a system to run this so if you face anything comment below.