TypeError: __init__() missing 2 required positional arguments: 'sequence_name' and 'sequence_category'

[yty-sky]

"/home/sheepsky/miniconda3/envs/pts_diffusion/lib/python3.8/site-packages/accele
rate/utils/operations.py", line 171, in send_to_device
return type(tensor)(
TypeError: init() missing 2 required positional arguments: 'sequence_name'
and 'sequence_category'

[yty-sky]

how to slolve this?

[lukemelas]

This is "Common Issue #3" in https://github.com/lukemelas/projection-conditioned-point-cloud-diffusion#common-issues, the README has instructions on fixing it :)

[yty-sky]

I have solved this, we should replace send_to_device function to the following(not same with the solution in Common Issue 3):

def send_to_device(tensor, device, non_blocking=False, skip_keys=None):
"""
Recursively sends the elements in a nested list/tuple/dictionary of tensors to a given device.

Args:
tensor (nested list/tuple/dictionary of torch.Tensor):
The data to send to a given device.
device (torch.device):
The device to send the data to.

Returns:
The same data structure as tensor with all tensors sent to the proper device.
"""
if isinstance(tensor, (tuple, list)):
return honor_type(
tensor, (send_to_device(t, device, non_blocking=non_blocking, skip_keys=skip_keys) for t in tensor)
)
elif isinstance(tensor, Mapping):
from pytorch3d.implicitron.dataset.data_loader_map_provider import FrameData
if isinstance(skip_keys, str):
skip_keys = [skip_keys]
elif isinstance(tensor, (FrameData)):
if skip_keys is None:
skip_keys = []
return type(tensor)(
**{
k: t if k in skip_keys else send_to_device(t, device, non_blocking=non_blocking,skip_keys=skip_keys)
for k, t in tensor.items()
}
)
elif skip_keys is None:
skip_keys = []
return type(tensor)(
{
k: t if k in skip_keys else send_to_device(t, device, non_blocking=non_blocking, skip_keys=skip_keys)
for k, t in tensor.items()
}
)
elif hasattr(tensor, "to"):
try:
return tensor.to(device, non_blocking=non_blocking)
except TypeError: # .to() doesn't accept non_blocking as kwarg
return tensor.to(device)
else:
return tensor
'''

[surtantheta]

Hi @yty-sky ,
I tried applying your solution but the issue still persists. Can you help ?

[ziyuz-vision]

@yty-sky I encountered another issue after applying your solution. Any idea?

AttributeError: 'NoneType' object has no attribute 'sequence_point_cloud'

[szy4017]

@zzy0428 I met the same problem. Do you have any solution?
This is part of the error log.
`Error executing job with overrides: ['dataset.category=tv', 'dataloader.batch_size=24', 'dataloader.num_workers=8', 'run.vis_before_training=True', 'run.val_before_training=True', 'run.name=train__hydrant__ebs_24']
Traceback (most recent call last):
File "main.py", line 165, in main
loss = model(batch, mode='train')
File "/data/szy4017/miniconda3/envs/pcdiffusion/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/data/szy4017/miniconda3/envs/pcdiffusion/lib/python3.8/site-packages/accelerate/utils/operations.py", line 697, in forward
return model_forward(*args, **kwargs)
File "/data/szy4017/miniconda3/envs/pcdiffusion/lib/python3.8/site-packages/accelerate/utils/operations.py", line 685, in call
return convert_to_fp32(self.model_forward(*args, **kwargs))
File "/data/szy4017/miniconda3/envs/pcdiffusion/lib/python3.8/site-packages/torch/autocast_mode.py", line 12, in decorate_autocast
return func(*args, **kwargs)
File "/data/szy4017/code/projection-conditioned-point-cloud-diffusion/experiments/model/model.py", line 177, in forward
pc=batch.sequence_point_cloud,
AttributeError: 'NoneType' object has no attribute 'sequence_point_cloud'

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
wandb: Waiting for W&B process to finish... (failed 1).
wandb: You can sync this run to the cloud by running:
wandb: wandb sync /data/szy4017/code/projection-conditioned-point-cloud-diffusion/experiments/outputs/train__hydrant__ebs_24/2023-10-27--22-11-43/wandb/offline-run-20231027_221147-k045nwtg
wandb: Find logs at: ./wandb/offline-run-20231027_221147-k045nwtg/logs`

[alexdesko]

Hi all, I have the same error as @zzy0428 and @szy4017, namely
get_num_points return x.points_padded().shape[1] AttributeError: 'NoneType' object has no attribute 'points_padded'
in model/model_utils.py line 29.
Has anyone found a fix for this ?

[013292]

after following @yty-sky solution, I've run into the same issue as @alexdesko

Hi all, I have the same error as @zzy0428 and @szy4017, namely get_num_points return x.points_padded().shape[1] AttributeError: 'NoneType' object has no attribute 'points_padded' in model/model_utils.py line 29. Has anyone found a fix for this ?

@lukemelas Are there any hints for addressing this problem?