Non-official Pytorch implementation of the CREStereo(CVPR 2022 Oral).
Non-official Pytorch implementation of the CREStereo (CVPR 2022 Oral) model converted from the original MegEngine implementation.
update 2023/01/03:
# train DDP
# change 'dist' to True in /cfgs/train.yaml file
python -m torch.distributed.launch --nproc_per_node=8 train.py
# train DP
# change 'dist' to False in /cfgs/train.yaml file
python train.py
convert_weights.py
script. Place the MegEngine weights (crestereo_eth3d.mge) file into the models folder before the conversion.models/crestereo_eth3d.pth
file. If you want to run your model with ONNX, you need to run the convert_to_onnx.py script. The script has two parts: