ReekiLee

Hello! Thanks for your great work! I have a question about pre-train loss. When pre-training flow network unsupervisedly, flow network and depth-pose network are trained respectively using the same loss...

Question about pose prediction output in mono_model

2

Hello! Thanks for this great work! When training with mono_model, the output tensor size of the posenet is [B, 2, 1, 3] for both axisangle and translation. But when calculating...

RuntimeError: CUDA error: out of memory

1

Hello！ Thanks for your great code! However, I met a bug. I prepared the enviroment and installed it according to your README file, after that I ran demo.py, and I...