Skip to content

Latest commit

 

History

History
 
 

lap-depth

README.md

LapDepth

Input

KITTI dataset image

Input

(Image from https://github.com/tjqansthd/LapDepth-release/blob/master/example/kitti_demo.jpg)

NYU dataset image

Input

(Image from https://github.com/tjqansthd/LapDepth-release/blob/master/example/nyu_demo.jpg)

Output

KITTI dataset image (by model_type kitti)

Input

NYU dataset image (by model_type nyu)

Input

Usage

Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.

For the sample image,

$ python3 lap-depth.py

If you want to specify the input image, put the image path after the --input option.
You can use --savepath option to change the directory of the output file to be saved.

$ python3 lap-depth.py --input IMAGE_PATH --savepath SAVE_IMAGE_PATH

By adding the --video option, you can input the video and convert it by the style image. If you pass 0 as an argument to VIDEO_PATH, you can use the webcam input instead of the video file.

$ python3 lap-depth.py --video VIDEO_PATH

You can specify the "model type" by specifying after the --model_type option. The model type is selected from "kitti", "kitti-grad", "nyu".

$ python3 lap-depth.py --model_type kitti

Reference

LapDepth-release

Framework

PyTorch

Model Format

ONNX opset = 11

Netron