SeokjuLee / Insta-DM

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency (AAAI 2021)
Other
220 stars 27 forks source link

Visualize in breakpoint 1 #10

Open fengziyue opened 2 years ago

fengziyue commented 2 years ago

Hi @SeokjuLee :

Thank you for sharing this amazing work, the visualization in this code helps me a lot in understanding the logic. However, I have a confusion, the line below: https://github.com/SeokjuLee/Insta-DM/blob/95fac7f3826045ccf36af12bb4b96b3868bd48ef/train.py#L402 will trigger the error "TypeError: Invalid shape (256, 832, 2) for image data"

There are two instance masks in r2t_inst, are you supposed to visualize one of them like r2t_inst[:, :, 0] or do you have other implementations to visualize both of them in once?

Thank you!