Test_shape failed with torchsparse 1.2 about adelaidepth HOT 5 CLOSED

Hi,
Can any help me to sort out this issue?
I got the same "ValueError: not enough values to unpack (expected 2, got 1)" error.
Though I tried with both torchsparse v1.2 and v1.4. but facing the same issue.

from adelaidepth.

Hey you can replace first line with second line with torchsparse==1.4
Replace this:
from torchsparse.utils import sparse_collate_fn, sparse_quantize
with this:
from torchsparse.utils.collate import sparse_collate_fn from torchsparse.utils.quantize import sparse_quantize

It'll work with torchsparse==1.4

from adelaidepth.

Hey,
Please check for default values for models in the test_shape.py and test_depth.py scripts.
Those values are different (resnet50 and resnet101), and they have to be the same.

from adelaidepth.

@isamabdullah88 What do you mean by default values? the values are the same
@YoushaaMurhij Can you please share how you solved this?

from adelaidepth.

@Ir1d

• Firstly move the model files to specified location and make sure the weight files are being read by the script. Place a check in code for that. I think the above error happens because of weight files not available.
• Then, make sure that --load_ckpt and --backbone both use the same model. (Either resnet101.pth or resnet50.pth).

Hope this helps!

from adelaidepth.