(Image from http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d)
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 did_m3d.py
if you want to --savepath option to change the name of the output file to save.
$ python3 did_m3d.py --savepath SAVE_IMAGE_PATH
If you want to specify the input image, put the image path after the --input
option.
$ python3 did_m3d.py --input IMAGE_PATH
The depth file and calib file are automatically found in the predetermined path.
If you want to specify directory or directly file path, put the path after the --calib_path
option.
$ python3 did_m3d.py --input IMAGE_PATH --calib_path CALIB_PATH
By adding the --video
option, you can input the video.
If you pass 0
as an argument to VIDEO_PATH, you can use the webcam input instead of the video file.
$ python3 did_m3d.py --video VIDEO_PATH
Pytorch
ONNX opset=12