antoalli/deco

DeCo: Denoise and Contrast for Category Agnostic Shape Completion

deco's Issues

Test code

Dear Antonio Alliegro:
I'm very sorry to bother you. I want to ask you to provide the test code.
Best wish to you.

Questions about the visualization of Figure 3 in the paper

I want to know how the point cloud visualization in Figure 3 in the paper is done, and what open source library or software is used?

How long does it take to get fully trained?

Hi, I have two questions. 1. What GPUs you were using? 2. How long did it take to get fully trained?

CUDNN_STATUS_MAPPING_ERROR while training the DeCo model

Hi antoalli,

I have the following error when I tried to train the Deco model using python train_deco.py --data_root data/shapenetcore_partanno_segmentation_benchmark_v0 --exp_name deco1280_512_wFrame512_sn13 --config configs/deco_config.json --parallel -P1 1280 -P2 512 --raw_weight 1 :

Arguments: Namespace(batch_size=30, checkpoints_dir='experiments_deco', class_choice='Airplane,Bag,Cap,Car,Chair,Guitar,Lamp,Laptop,Motorbike,Mug,Pistol,Skateboard,Table', config='configs/deco_config.json', context_point_num=512, crop_point_num=512, data_root='data/shapenetcore_partanno_segmentation_benchmark_v0', epochs=241, exp_name='deco1280_512_wFrame512_sn13_0', fps_centroids=False, it_test=10, manualSeed=7926, models_dir='experiments_deco/deco1280_512_wFrame512_sn13_0/models', num_holes=1, parallel=True, pool1_points=1280, pool2_points=512, raw_weight=1.0, restart_from='', save_dir='experiments_deco/deco1280_512_wFrame512_sn13_0', vis_dir='experiments_deco/deco1280_512_wFrame512_sn13_0/train_visz', workers=12)
Configuration: {'global_encoder': {'nearest_neighboors': 24, 'latent_dim': 1024}, 'generator': {'latent_dim': 256, 'nearest_neighboors': 16, 'pool1_nn': 16, 'pool2_nn': 6, 'scoring_fun': 'tanh'}, 'completion_trainer': {'checkpoint_global_enco': 'pretext_weights/global_contrastive/cropRotScaleJitt_4pos_1602780721.pth', 'checkpoint_local_enco': 'pretext_weights/gpd_local_denoising/gpd_residual_nn8_mse_ep100.pth', 'data_root': '/home/antonioa/data/shapenetcore_partanno_segmentation_benchmark_v0', 'num_points': 2048, 'enco_lr': 0.001, 'enco_step': 25, 'gen_lr': 0.001, 'gen_step': 40}, 'GPD_local': {'pre_Nfeat': [3, 33, 66, 99], 'conv_n_layers': 3, 'conv_layer': {'in_feat': 99, 'fnet_feat': 99, 'out_feat': 99, 'rank_theta': 11, 'stride_th1': 33, 'stride_th2': 33, 'min_nn': 8}}}
Class choice list: ['Airplane', 'Bag', 'Cap', 'Car', 'Chair', 'Guitar', 'Lamp', 'Laptop', 'Motorbike', 'Mug', 'Pistol', 'Skateboard', 'Table']
Training Completion Task...
Local FE pretrained weights - loading res: _IncompatibleKeys(missing_keys=[], unexpected_keys=['l_conv.sl_W', 'l_conv.sl_b', 'l_conv.gconv.W_flayer_th0', 'l_conv.gconv.b_flayer_th0', 'l_conv.gconv.W_flayer_th1', 'l_conv.gconv.b_flayer_th1', 'l_conv.gconv.W_flayer_th2', 'l_conv.gconv.b_flayer_th2', 'l_conv.gconv.W_flayer_thl', 'l_conv.gconv.b_flayer_thl'])
Global FE pretrained weights - loading res: <All keys matched successfully>
Num GPUs: 4, Parallelism: True
Centroids: [[ 1  0  0]
 [ 0  0  1]
 [ 1  0  1]
 [-1  0  0]
 [-1  1  0]]
Training.. 
Traceback (most recent call last):
  File "train_deco.py", line 437, in <module>
    main_worker()  # train DeCo
  File "train_deco.py", line 309, in main_worker
    feat = gl_encoder(partials)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 152, in forward
    outputs = self.parallel_apply(replicas, inputs, kwargs)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 162, in parallel_apply
    return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py", line 85, in parallel_apply
    output.reraise()
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/_utils.py", line 369, in reraise
    raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in replica 0 on device 0.
Original Traceback (most recent call last):
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker
    output = module(*input, **kwargs)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/$USER/Deco/models/model_deco.py", line 94, in forward
    l_feat = self.local_encoder(points)  # [B, 99, N]
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/$USER/Deco/models/model_deco.py", line 49, in forward
    h = self.pre_nn_layers(points)  # [B, in_feat, N]
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/$USER/miniconda3/envs/deco_env/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 200, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: cuDNN error: CUDNN_STATUS_MAPPING_ERROR

Environment:
System: Ubuntu 20.04.3
Python: 3.7.9
PyTorch: 1.2.0
CUDA Version: 11.4
gcc version 9.3.0

I highly appreciate your help regarding this error. Let me know if you need any other information.

Problems in the code of pre-training networks and datasets

Can you provide the code of pre-training networks and datasets?

Question About the paper

Hi ! I don't quite understand what 'frame' stands for.
Could you please tell me something about its function.
Thanks a lot

Problem in installing Chamfer distance package

I have the following error after running python build.py install from models/torch-nndistance:
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h:2087:1: note: template argument deduction/substitution failed:
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h:2094:1: note: candidate: template<pybind11::return_value_policy policy, class ... Args, class> pybind11::detail::unpacking_collector pybind11::detail::collect_arguments(Args&& ...)
unpacking_collector collect_arguments(Args &&...args) {
^
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h:2094:1: note: template argument deduction/substitution failed:
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h: In instantiation of ‘pybind11::object pybind11::detail::object_api::operator()(Args&& ...) const [with pybind11::return_value_policy policy = (pybind11::return_value_policy)1u; Args = {pybind11::object&, const pybind11::handle&}; Derived = pybind11::detail::accessorpybind11::detail::accessor_policies::str_attr]’:
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/pytypes.h:923:28: required from ‘pybind11::str pybind11::str::format(Args&& ...) const [with Args = {pybind11::object&, const pybind11::handle&}]’
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/pybind11.h:1401:51: required from here
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h:2108:44: error: no matching function for call to ‘collect_arguments(pybind11::object&, const pybind11::handle&)’
return detail::collect_arguments(std::forward(args)...).call(derived().ptr());
^
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h:2087:1: note: candidate: template<pybind11::return_value_policy policy, class ... Args, class> pybind11::detail::simple_collector pybind11::detail::collect_arguments(Args&& ...)
simple_collector collect_arguments(Args &&...args) {
^
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h:2087:1: note: template argument deduction/substitution failed:
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h:2094:1: note: candidate: template<pybind11::return_value_policy policy, class ... Args, class> pybind11::detail::unpacking_collector pybind11::detail::collect_arguments(Args&& ...)
unpacking_collector collect_arguments(Args &&...args) {
^
/home/liuhw@1/anaconda3/envs/deco/lib/python3.7/site-packages/torch/include/pybind11/cast.h:2094:1: note: template argument deduction/substitution failed:
error: command '/cm/shared/apps/cuda91/toolkit/9.1.85/bin/nvcc' failed with exit status 1
Here is the last part of the code.

Environment:
System: centOS
Python: 3.7.9
PyTorch: 1.2.0
CUDA Version: 10.0
gcc version 5.5

I would be very grateful if you could give me some help.

How to visualize point cloud instances shown in your paper?

Hi!
It is an interesting work that exploits SSL to perform 3D point cloud completion task.
The visualization results in Figure 3 are very impressive, how do I render point cloud instances like this? Could you share the code or some instructions?
Thanks a lot.