grobenis / monodepth2_cpp

Add Monodepth2 to Project as a Module

Monodepth2.cpp

This is a simple inference implementation for a well-known depth estimation network written in C++. The whole project is based on libtorch API.

steps to run this simple project

1. download related libraries including OpenCV and libtorch.
2. download my converted torchscript model or convert your trained model into torchscript by yourself. If you don't familiar with torchscript currently, please check the offical docs
3. prepare a sample image and change its path in main.cpp
4. if you don't have available gpus, please annotate CUDA options in CMakeLists.txt

dockerfile

If you're familiar with docker, you could run this project withour the need of installing those libraries. please remember install nvidia-docker because our projects needs to use gpus.

Converted models

you could follow to_jit.py to create your own torchscript model and use my converted model directly.
monodepth2
packnet-sfm