Issues
- 0
使用kitti数据集训练psmnet时似乎有问题，使用train.py训练时打印出的eval数据集的epe过低（一点几，和loss相近），使用eval.py打印出的eval数据集的epe过高（三十几），这与许多论文的结果不一致
#101 opened by XianghuiFan - 1
Middlebury dataset download issue
#96 opened by zhangzscn - 1
The size of tensor a (156) must match the size of tensor b (155) at non-singleton dimension 4
#100 opened by lixxxxj - 1
Inference on single image
#88 opened by saqib736 - 1
The desgin is not inference friendly.
#98 opened by luxunxiansheng - 1
Plan about model deployment
#92 opened by Daa98 - 1
- 1
关于复现StereoBase
#94 opened by shengwenbo125 - 1
Mistake in paper table7
#95 opened by Guptajakala - 1
- 5
Evaluation on ETH3D, MB and KITTI
#47 opened by TomTomTommi - 1
The training strategies
#83 opened by zhuxing0 - 1
Which pretrained model exactly is stereo base?
#81 opened by Rong-Tao - 1
Configuration file for the DrivingStereo dataset.
#84 opened by Tobyzai - 1
KITTI benchmark sota is based on which model?
#79 opened by ziming-liu - 1
- 2
sttr, epe is tool large
#62 opened by arminghz - 2
- 2
- 1
- 1
- 5
- 1
FADNet tensor size mismatched
#53 opened by lykasbongbongbong - 1
Have you tried converting the PyTorch model via ONNX to a TensorRT engine for faster inference?
#54 opened by spinzello