search

TRI-ML / packnet-sfm

TRI-ML Monocular Depth Estimation Repository
https://tri-ml.github.io/packnet-sfm/
MIT License
1.24k stars 243 forks source link

Does this result looks normal? #145

Closed lucasjinreal closed 2 years ago

lucasjinreal commented 3 years ago

image

the RGBD 3D looks weired.

lucasjinreal commented 3 years ago

the orange car almost same as ground

VitorGuizilini-TRI commented 3 years ago

Yeah, it is definitely off, but the depth map looks OK. How are you doing the pointcloud reconstruction?

lucasjinreal commented 3 years ago

image

Does this looks normal? (I think the width is not good) this is DDAD_tiny

But I fixed kitti, it looks normal now:

image

porwalnaman01 commented 3 years ago

@jinfagang Hello there, did you receive this error while training, if yes then how did you solve it?

Traceback (most recent call last): File "scripts/train.py", line 68, in train(args.file) File "scripts/train.py", line 63, in train trainer.fit(model_wrapper) File "/disk1/dan/Naman/packnet-sfm/packnet_sfm/trainers/horovod_trainer.py", line 65, in fit validation_output = self.validate(val_dataloaders, module) File "/disk1/dan/Naman/packnet-sfm/packnet_sfm/trainers/horovod_trainer.py", line 120, in validate output = module.validation_step(batch, i, n) File "/disk1/dan/Naman/packnet-sfm/packnet_sfm/models/model_wrapper.py", line 194, in validation_step output = self.evaluate_depth(batch) File "/disk1/dan/Naman/packnet-sfm/packnet_sfm/models/model_wrapper.py", line 302, in evaluate_depth inv_depths[0], inv_depths_flipped[0], method='mean') File "/disk1/dan/Naman/packnet-sfm/packnet_sfm/utils/depth.py", line 247, in post_process_inv_depth B,C, H, W = inv_depth.shape ValueError: not enough values to unpack (expected 4, got 3)

VitorGuizilini-TRI commented 3 years ago

Did you solve it?