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

[NTheodoris]

**When i try to run demo.py in conda envionment, i get this error ******

Warp 1.0.2 initialized:
CUDA Toolkit 11.5, Driver 12.4
Devices:
"cpu" : "x86_64"
"cuda:0" : "NVIDIA GeForce RTX 3060" (12 GiB, sm_86, mempool enabled)
Kernel cache:
/home/lms/.cache/warp/1.0.2
[init()] self.cfg:
lr: 0.0001
c_in: 6
zfar: 'Infinity'
debug: null
n_view: 1
run_id: 3wy8qqex
use_BN: true
exp_name: 2024-01-11-20-02-45
n_epochs: 62
save_dir: /home/bowenw/debug/2024-01-11-20-02-45/
use_mask: false
loss_type: pairwise_valid
optimizer: adam
batch_size: 64
crop_ratio: 1.1
enable_amp: true
use_normal: false
max_num_key: null
warmup_step: -1
input_resize:

• 160
• 160
  max_step_val: 1000
  vis_interval: 1000
  weight_decay: 0
  normalize_xyz: true
  resume_run_id: null
  clip_grad_norm: 'Infinity'
  lr_epoch_decay: 500
  render_backend: nvdiffrast
  train_num_pair: 5
  lr_decay_epochs:
• 50
  n_epochs_warmup: 1
  make_pair_online: false
  gradient_max_norm: 'Infinity'
  max_step_per_epoch: 10000
  n_rendering_workers: 1
  save_epoch_interval: 100
  n_dataloader_workers: 100
  split_objects_across_gpus: true
  ckpt_dir: /home/lms/Github/deep_learning_vision_methods/src/foundation_pose6d/learning/training/../../weights/2024-01-11-20-02-45/model_best.pth

[init()] self.h5_file:None
[init()] Using pretrained model from /home/lms/Github/deep_learning_vision_methods/src/foundation_pose6d/learning/training/../../weights/2024-01-11-20-02-45/model_best.pth
[init()] init done
[init()] welcome
[init()] self.cfg:
lr: 0.0001
c_in: 6
zfar: .inf
debug: null
w_rot: 0.1
n_view: 1
run_id: null
use_BN: true
rot_rep: axis_angle
ckpt_dir: /home/lms/Github/deep_learning_vision_methods/src/foundation_pose6d/learning/training/../../weights/2023-10-28-18-33-37/model_best.pth
exp_name: 2023-10-28-18-33-37
save_dir: /tmp/2023-10-28-18-33-37/
loss_type: l2
optimizer: adam
trans_rep: tracknet
batch_size: 64
crop_ratio: 1.2
use_normal: false
BN_momentum: 0.1
max_num_key: null
warmup_step: -1
input_resize:

• 160
• 160
  max_step_val: 1000
  normal_uint8: false
  vis_interval: 1000
  weight_decay: 0
  n_max_objects: null
  normalize_xyz: true
  clip_grad_norm: 'Infinity'
  rot_normalizer: 0.3490658503988659
  trans_normalizer:
• 0.019999999552965164
• 0.019999999552965164
• 0.05000000074505806
  max_step_per_epoch: 25000
  val_epoch_interval: 10
  n_dataloader_workers: 60
  enable_amp: true
  use_mask: false

[init()] self.h5_file:
[init()] Using pretrained model from /home/lms/Github/deep_learning_vision_methods/src/foundation_pose6d/learning/training/../../weights/2023-10-28-18-33-37/model_best.pth
[init()] init done
[reset_object()] self.diameter:0.19646325799497472, vox_size:0.009823162899748735
[reset_object()] self.pts:torch.Size([607, 3])
[reset_object()] reset done
[make_rotation_grid()] cam_in_obs:(42, 4, 4)
[make_rotation_grid()] rot_grid:(252, 4, 4)
Traceback (most recent call last):
File "/home/lms/Github/deep_learning_vision_methods/src/foundation_pose6d/run_demo.py", line 41, in
est = FoundationPose(model_pts=mesh.vertices, model_normals=mesh.vertex_normals, mesh=mesh, scorer=scorer, refiner=refiner, debug_dir=debug_dir, debug=debug, glctx=glctx)
File "/home/lms/Github/deep_learning_vision_methods/src/foundation_pose6d/estimater.py", line 27, in init
self.make_rotation_grid(min_n_views=40, inplane_step=60)
File "/home/lms/Github/deep_learning_vision_methods/src/foundation_pose6d/estimater.py", line 120, in make_rotation_grid
rot_grid = mycpp.cluster_poses(30, 99999, rot_grid, self.symmetry_tfs.data.cpu().numpy())
AttributeError: 'NoneType' object has no attribute 'cluster_poses'

[juwangvsu]

I have the same problem (4070), would you mind sharing your solution if you have solved the issue?

[juwangvsu]

never mind, find a solution at #89. clean rebuild mycpp after the 4090 hack

[MY-CODE-1981]

CMAKE_PREFIX_PATH=$CONDA_PREFIX/lib/python3.9/site-packages/pybind11/share/cmake/pybind11 bash build_all_conda.sh
After this procedure, a .so file will be created under mycpp/build. If its name is not mycpp.so, an error will occur when executing mycpp.cluster_poses in estimator.py.

The solution is simple: just rename the .so file to mycpp.so. In my case, the name was as follows, and changing it to mycpp.so resolved the issue:
mycpp.cpython-39-x86_64-linux-gnu.so

[Cheney-36]

My 40 series graphics card can run the following command without modifying the so file nameCMAKE_PREFIX_PATH=$CONDA_PREFIX/lib/python3.9/site-packages/pybind11/share/cmake/pybind11 bash build_all_conda.sh