Closed mslavescu closed 3 years ago
same error here
Our models were trained using driving datasets, so it's expected that they do not transfer well to these new domains. You would have to train new models on more diverse datasets (like MiDaS did), to achieve this level of accuracy.
About the error, seems like the pre-trained models use a different name for the encoder, and you try explicitly setting the network in your config file during inference? The training scripts provide the correct configuration, you can use those for inference as well.
Hi,
I setup the docker same as here: https://github.com/TRI-ML/packnet-sfm/issues/154#issue-928707614
I wownloaded all these 4 checkpoints in /data/checkpoints
And I tested this image with PackNetSAN01_HR_sup_K.ckpt and ResNet18_MR_selfsup_D.ckpt
And I got these results:
When I ran the same image with MiDaS v3 I get this result, which looks much better than those above:
How can I get similar depth or better than MiDaS v3 using packnet-sfm on non KITTI images?
It works fine on KITTI tiny images as I shown here: https://github.com/TRI-ML/packnet-sfm/issues/154#issuecomment-867254872
If I run with PackNetSAN01_HR_sup_K.ckpt I get this error:
Same issue with PackNetSAN01_HR_sup_D.ckpt: