Skip to content

Python scripts form performing stereo depth estimation using the HITNET model in ONNX.

License

Notifications You must be signed in to change notification settings

ibaiGorordo/ONNX-HITNET-Stereo-Depth-estimation

Repository files navigation

ONNX-HITNET-Stereo-Depth-estimation

Python scripts form performing stereo depth estimation using the HITNET model in ONNX.

Hitnet stereo depth estimation ONNX Stereo depth estimation on the cones images from the Middlebury dataset (https://vision.middlebury.edu/stereo/data/scenes2003/)

Requirements

Installation

pip install -r requirements.txt
pip install pafy youtube-dl

ONNX model

The original models were converted to different formats (including .onnx) by PINTO0309, download the models from his repository and save them into the models folder.

Original Tensorflow model

The Tensorflow pretrained model was taken from the original repository.

Examples

  • Depthai OAK-D series inference on the host:
python depthai_host_depth_estimation.py
  • Image inference:
python image_depth_estimation.py 
  • Video inference:
python video_depth_estimation.py
  • DrivingStereo dataset inference:
python driving_stereo_test.py

Pytorch inference

For performing the inference in Tensorflow, check my other repository HITNET Stereo Depth estimation.

TFLite inference

For performing the inference in TFLite, check my other repository TFLite HITNET Stereo Depth estimation.

Hitnet stereo depth estimation ONNX

References:

Releases

No releases published

Packages

No packages published

Languages