Closed jokokojote closed 2 years ago
I'm not a contributor, but why do you load checkpoints to your models twice, moreover from different locations:
model = ml3d.models.KPFCNN(ckpt_path=ckpt_path_k) # This is the one that was downloaded.
...
pipeline_k.load_ckpt(model.cfg.ckpt_path) # Maybe ckpt_path_k should go here?
Also, there is another issue on trained models size mismatch: https://github.com/isl-org/Open3D-ML/issues/364
@kukuruza thanks for your suggestion.
I understand what you mean, but it is done the same way in examples/vis_pred.py, isn‘t it?
But you are right, #364 seems to be the same problem. My fault.
@jokokojote Thankyou for reporting this issue. Let me try to reproduce and get back to you.
@jokokojote I cannot reproduce this issue with the default config. You need to use config files present in ml3d/configs/randlanet_s3dis.yml
for network parameters.
A quick and better way to train/test your model is through our predefined script. Here https://github.com/isl-org/Open3D-ML#using-predefined-scripts
Closing due to inactivity.
I have problems using the pretrained weights for the s3dis dataset (both randlanet and kpconv).
Min. example (including downloads like given in model_zoo.md):
Error outputs:
randlanet torch:
kpconv torch:
randlanet tf:
kpconv tf:
Did I mess up the files or this there something wrong with the checkpoints?