svip-lab / PlaneDepth

[CVPR2023] This is an official implementation for "PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes".
Other
102 stars 5 forks source link

can't find a suitable pretrained model #13

Closed seemaywang closed 8 months ago

seemaywang commented 1 year ago

Thanks for your impressive work! when I tested on custmo model,"load_state_dict(torch.load(os.path.join(opt.load_weights_folder, "plade.pth")))", but it seems like no pretrained model end with"plade.pth", could you please tell me which model is matched with PladeNet, thankyou!

Dwawayu commented 1 year ago

Hi! I apologize for the delayed response. The code segment you have referred to was part of our early experiments to test different network architectures and is now obsolete. You may need to update the plade_net.py according to depth_decoder.py and train a new ckpt with the flag --net_type PladeNet.

Please do not hesitate to contact me if you have any further issues.

seemaywang commented 1 year ago

Thanks a lot!!!