ocnn 2.2.0__py3-none-any.whl → 2.2.2__py3-none-any.whl

{ocnn-2.2.0.dist-info → ocnn-2.2.2.dist-info}/METADATA

@@ -1,65 +1,67 @@
-Metadata-Version: 2.1
-Name: ocnn
-Version: 2.2.0
-Summary: Octree-based Sparse Convolutional Neural Networks
-Home-page: https://github.com/octree-nn/ocnn-pytorch
-Author: Peng-Shuai Wang
-Author-email: wangps@hotmail.com
-License: MIT
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.6
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: torch
-Requires-Dist: numpy
-
-# O-CNN
-
-**[Documentation](https://ocnn-pytorch.readthedocs.io)**
-
-[![Documentation Status](https://readthedocs.org/projects/ocnn-pytorch/badge/?version=latest)](https://ocnn-pytorch.readthedocs.io/en/latest/?badge=latest)
-[![downloads](https://pepy.tech/badge/ocnn)](https://pepy.tech/project/ocnn)
-[![PyPI](https://img.shields.io/pypi/v/ocnn)](https://pypi.org/project/ocnn/)
-
-This repository contains the **pure PyTorch**-based implementation of
-[O-CNN](https://wang-ps.github.io/O-CNN.html). The code has been tested with
-`Pytorch>=1.6.0`, and `Pytorch>=1.9.0` is preferred.
-
-O-CNN is an octree-based sparse convolutional neural network framework for 3D
-deep learning. O-CNN constrains the CNN storage and computation into non-empty
-sparse voxels for efficiency and uses the `octree` data structure to organize
-and index these sparse voxels.
-
-The concept of sparse convolution in O-CNN is the same with
-[H-CNN](https://ieeexplore.ieee.org/abstract/document/8580422),
-[SparseConvNet](https://openaccess.thecvf.com/content_cvpr_2018/papers/Graham_3D_Semantic_Segmentation_CVPR_2018_paper.pdf),
-and
-[MinkowskiNet](https://openaccess.thecvf.com/content_CVPR_2019/papers/Choy_4D_Spatio-Temporal_ConvNets_Minkowski_Convolutional_Neural_Networks_CVPR_2019_paper.pdf).
-The key difference is that our O-CNN uses the `octree` to index the sparse
-voxels, while these 3 works use the `Hash Table`.
-
-Our O-CNN is published in SIGGRAPH 2017, H-CNN is published in TVCG 2018,
-SparseConvNet is published in CVPR 2018, and MinkowskiNet is published in 
-CVPR 2019. Actually, our O-CNN was submitted to SIGGRAPH in the end of 2016 and
-was officially accepted in March, 2017. The camera-ready version of our O-CNN was
-submitted to SIGGRAPH in April, 2017. We just did not post our paper on Arxiv
-during the review process of SIGGRAPH. Therefore, **the idea of constraining CNN
-computation into sparse non-emtpry voxels is first proposed by our O-CNN**.
-Currently, this type of 3D convolution is known as Sparse Convolution in the
-research community. 
-
-## Key benefits of ocnn-pytorch
-
-- **Simplicity**. The ocnn-pytorch is based on pure PyTorch, it is portable and
-  can be installed with a simple command:`pip install ocnn`. Other sparse
-  convolution frameworks heavily rely on C++ and CUDA, and it is complicated to
-  configure the compiling environment.
-
-- **Efficiency**. The ocnn-pytorch is very efficient compared with other sparse
-  convolution frameworks.  It only takes 18 hours to train the network on
-  ScanNet for 600 epochs with 4 V100 GPUs. For reference, under the same
-  training settings, MinkowskiNet 0.4.3 takes 60 hours and MinkowskiNet 0.5.4
-  takes 30 hours.
-
+Metadata-Version: 2.1
+Name: ocnn
+Version: 2.2.2
+Summary: Octree-based Sparse Convolutional Neural Networks
+Home-page: https://github.com/octree-nn/ocnn-pytorch
+Author: Peng-Shuai Wang
+Author-email: wangps@hotmail.com
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch
+Requires-Dist: torchvision
+Requires-Dist: numpy
+Requires-Dist: packaging
+
+# O-CNN
+
+**[Documentation](https://ocnn-pytorch.readthedocs.io)**
+
+[![Documentation Status](https://readthedocs.org/projects/ocnn-pytorch/badge/?version=latest)](https://ocnn-pytorch.readthedocs.io/en/latest/?badge=latest)
+[![Downloads](https://static.pepy.tech/badge/ocnn)](https://pepy.tech/project/ocnn)
+[![PyPI](https://img.shields.io/pypi/v/ocnn)](https://pypi.org/project/ocnn/)
+
+This repository contains the **pure PyTorch**-based implementation of
+[O-CNN](https://wang-ps.github.io/O-CNN.html). The code has been tested with
+`Pytorch>=1.6.0`, and `Pytorch>=1.9.0` is preferred.
+
+O-CNN is an octree-based sparse convolutional neural network framework for 3D
+deep learning. O-CNN constrains the CNN storage and computation into non-empty
+sparse voxels for efficiency and uses the `octree` data structure to organize
+and index these sparse voxels.
+
+The concept of sparse convolution in O-CNN is the same with
+[H-CNN](https://ieeexplore.ieee.org/abstract/document/8580422),
+[SparseConvNet](https://openaccess.thecvf.com/content_cvpr_2018/papers/Graham_3D_Semantic_Segmentation_CVPR_2018_paper.pdf),
+and
+[MinkowskiNet](https://openaccess.thecvf.com/content_CVPR_2019/papers/Choy_4D_Spatio-Temporal_ConvNets_Minkowski_Convolutional_Neural_Networks_CVPR_2019_paper.pdf).
+The key difference is that our O-CNN uses the `octree` to index the sparse
+voxels, while these 3 works use the `Hash Table`.
+
+Our O-CNN is published in SIGGRAPH 2017, H-CNN is published in TVCG 2018,
+SparseConvNet is published in CVPR 2018, and MinkowskiNet is published in 
+CVPR 2019. Actually, our O-CNN was submitted to SIGGRAPH in the end of 2016 and
+was officially accepted in March, 2017. The camera-ready version of our O-CNN was
+submitted to SIGGRAPH in April, 2017. We just did not post our paper on Arxiv
+during the review process of SIGGRAPH. Therefore, **the idea of constraining CNN
+computation into sparse non-emtpry voxels is first proposed by our O-CNN**.
+Currently, this type of 3D convolution is known as Sparse Convolution in the
+research community. 
+
+## Key benefits of ocnn-pytorch
+
+- **Simplicity**. The ocnn-pytorch is based on pure PyTorch, it is portable and
+  can be installed with a simple command:`pip install ocnn`. Other sparse
+  convolution frameworks heavily rely on C++ and CUDA, and it is complicated to
+  configure the compiling environment.
+
+- **Efficiency**. The ocnn-pytorch is very efficient compared with other sparse
+  convolution frameworks.  It only takes 18 hours to train the network on
+  ScanNet for 600 epochs with 4 V100 GPUs. For reference, under the same
+  training settings, MinkowskiNet 0.4.3 takes 60 hours and MinkowskiNet 0.5.4
+  takes 30 hours.
+

ocnn-2.2.2.dist-info/RECORD

@@ -0,0 +1,36 @@
+ocnn/__init__.py,sha256=3vM-r35p3glXfQ00Pqe13Loig8b8zk17l-_lw2npsP0,582
+ocnn/dataset.py,sha256=wvclvjlZs9qTeMXWLaO32K5d1VVY9XHSNuVVJEpVeeo,5266
+ocnn/utils.py,sha256=w6IrVsBMAL5JuBUxg1BtcuWkCpy8Fo5LkYG6arYpFkc,6618
+ocnn/models/__init__.py,sha256=F9PJRhOPHc1OrwkqcfywEBW0J6jmVW7-IHgWjGpY15U,724
+ocnn/models/autoencoder.py,sha256=TjOet3dbZLexz-PvZdeV0mbIuGpUAeSH6KWU_z_s-d8,5906
+ocnn/models/hrnet.py,sha256=9W2fi7Fuw0JXDBiZtEoUW2K7ghtpWUm_BWd-mKoHLY0,6684
+ocnn/models/image2shape.py,sha256=5djcOHJh2SQCwd5XdLPeL5vlQDNWnRU3tJY3ojRI8aQ,4589
+ocnn/models/lenet.py,sha256=oryTVauF48biFIJY163d15JNTYHU4M_gBHUWKDM9n7Q,1754
+ocnn/models/ounet.py,sha256=sGGVHqF1nKw798vyththxp7-P3wHlsDUO39hbQpUVTw,3303
+ocnn/models/resnet.py,sha256=9gZKbhFituqPJHCm-bp1xTtHKZ6wu77s31a0q7RtXoQ,2029
+ocnn/models/segnet.py,sha256=VfZf8gBMSPgO5m8Agsfccw9snTrI4LGh0SqxhLZ1F8s,2575
+ocnn/models/unet.py,sha256=1FZbTvmWg6sMYkcZyNxcSr_qN6bfOOag-tIwAoqIPKU,4123
+ocnn/modules/__init__.py,sha256=BAEZybvtwDQf7yPZpGcptH1Oxf654Alq87G9D0vKw-E,820
+ocnn/modules/modules.py,sha256=7VlBsbwN49J8Xea0DXcFHVhN8POxhzC3FNMY3_JHukM,6207
+ocnn/modules/resblocks.py,sha256=Xh5EH6aSx8zcLk3D4m4lZiWDejLMu5AQDH7ZDI4p23A,4548
+ocnn/nn/__init__.py,sha256=rmdXQiUa9-GVvVoAxDYf2uTc0yeiwW67BCgOgnqzn60,1707
+ocnn/nn/octree2col.py,sha256=07BGGJD0je0VD-VdS_aKtDo7gWKNWdgojeL1a2n4VRQ,2137
+ocnn/nn/octree2vox.py,sha256=QgyxxZvRvw2taHFWCvcGyCFAnFC6D6nfw71HrvwN3PI,1524
+ocnn/nn/octree_align.py,sha256=Y12GBKS-F3JtRNaDdDcBFDBvhndoRxeMOVua4RB5HZE,1696
+ocnn/nn/octree_conv.py,sha256=rylone_moG8oiWrhb4YYfTgtKcFqHyQ_hCk-VgGzvzI,14468
+ocnn/nn/octree_drop.py,sha256=croMHtk0JScDT0nLpdmbiMnkM_b5uVAz6sOEUcta6sY,1963
+ocnn/nn/octree_dwconv.py,sha256=lXwDtcIYUSjuY4qBGIMOsWHYBr5V7L6RFc78B0z8Ki8,6876
+ocnn/nn/octree_gconv.py,sha256=Ogkn7wE49dDdP0X_aBthNfJXMsqcRn3ufJuYQtEEjUI,2928
+ocnn/nn/octree_interp.py,sha256=yQVjiKMNLU1XakPeYjW5ArMsw2fxFRZdh90Nn3cWQuE,7108
+ocnn/nn/octree_norm.py,sha256=Mbn28Hv-CEWt2WA0Pdhj2p127m10vwhepzCJVjiZYMI,2976
+ocnn/nn/octree_pad.py,sha256=suV6Ftb-UlUuoJzKdQ9DCP9oqVQJq7vXb9_6hq-kUk4,1323
+ocnn/nn/octree_pool.py,sha256=Zn2XLk5SFl6pqMhhKIvu1uZl5ebonFSlPcKr54fOIPA,6664
+ocnn/octree/__init__.py,sha256=vKZFc5_r6Gxg5KsPWiCZCR-umWWfWPoE7qBx4PIrUGA,630
+ocnn/octree/octree.py,sha256=w5L3cfXIbyzzQEqC8JiVMX-Jyijh6DxhXulE4voKfm0,23722
+ocnn/octree/points.py,sha256=8yYHVc7E40qA8c3MGuI50k_51nwjg92PXXA3YRXt-LY,11121
+ocnn/octree/shuffled_key.py,sha256=UJZ4eKNA_7nLbf9FbEvS_3VyrAqnZCOzk1hsPtJianM,3936
+ocnn-2.2.2.dist-info/LICENSE,sha256=YeOS0Plo8Uistv_8ZXdgddmN9GHJKnIiJ5FZ8zTW6Sw,1114
+ocnn-2.2.2.dist-info/METADATA,sha256=tnq-YTGa06xrggKxndRvoe2GS5Hv6qIx65LKyQmF1HM,3297
+ocnn-2.2.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+ocnn-2.2.2.dist-info/top_level.txt,sha256=ayZdVOnxlOke3kgzAlrRh2IEL_qOudwOaEU3xhjtpZ0,5
+ocnn-2.2.2.dist-info/RECORD,,

{ocnn-2.2.0.dist-info → ocnn-2.2.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.38.4)
+Generator: bdist_wheel (0.43.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

ocnn-2.2.0.dist-info/RECORD

@@ -1,32 +0,0 @@
-ocnn/__init__.py,sha256=Zv5CZ9U_SMB2iTfxKpDadxx2e4VjQYglYCYXMVtfi2U,558
-ocnn/dataset.py,sha256=Nq6Qu-8MpEr_1W8EKvOQr09WqRXwjpfmS7FpC3fELSo,5036
-ocnn/utils.py,sha256=N95F2gqluWXad0J5zy9U-iDRVBe5A9m-YGgcGCiwKi0,4949
-ocnn/models/__init__.py,sha256=8r1yDRUHyVGLQHIfT8PIiLmlUjjCPgSg1FF0VE8V3DY,600
-ocnn/models/autoencoder.py,sha256=6pzfedwcLYyMrdDg2-1SkfQUxiJEnVYX-aTq4RLes3E,6028
-ocnn/models/hrnet.py,sha256=oLVDmnCG0DMrfCDLOHQJ0z7mugIG7NZZPJSR-pdi_s0,6429
-ocnn/models/lenet.py,sha256=Q_K3_MA5351IAiNC8u-rZv9Oqaxw0xTjw5tLv4ZxkIM,1708
-ocnn/models/resnet.py,sha256=NNjKrNN9WK0g9QkG8BEtNx-1NdURvtz3AgONktmFblA,1976
-ocnn/models/segnet.py,sha256=B9fmbxrGLUk89Mtau8bxWvasA4QKuX8kS_sXlJY-chA,2503
-ocnn/models/unet.py,sha256=zQi-e_3iblMq-1FwstRqDTdeG_nIAtGAc6xwzk6RzlA,4018
-ocnn/modules/__init__.py,sha256=3yBPDqJ82SIb-M42EmjWdE16g5huQp8PHp_y2rty1rk,800
-ocnn/modules/modules.py,sha256=M2mrrouttQ3hWj0A9-iFBeQPBXPQvSJySeloR2OFXFw,7433
-ocnn/modules/resblocks.py,sha256=coYMDc9_0EhhzAJ_EthNVkvif7rixe2yqBvcpdjoYSw,4424
-ocnn/nn/__init__.py,sha256=iLgcG8-3iE8PT9R5kcLEtNOlyMxZc7QV3XhM8ycUICc,1540
-ocnn/nn/octree2col.py,sha256=GAnUmCm0vqpvdoVhiteDizsjCUNIO0eIFEfWnFu4Z7A,2084
-ocnn/nn/octree2vox.py,sha256=I0VQpnqJlHaeEbsRBwKb8gnYRana8rSM3l-ypEuKAXI,1474
-ocnn/nn/octree_conv.py,sha256=hPBlJ4iKqsFsCzpU5V8TKn1Ifkrt6U9fKV-ZJ5TIN1U,14057
-ocnn/nn/octree_drop.py,sha256=KzlLNklPFQ9IAnWuvk4F6YQ8jg1P2vwgnsIeUE7eLzc,1908
-ocnn/nn/octree_dwconv.py,sha256=LIqQi4by4gR25W0Iyqt6Y35NnBrWUlykTKhPsbNQPjc,6672
-ocnn/nn/octree_interp.py,sha256=wQjh11HeHMTDdzb5csek1JzOtqIM0HLvEj_U8NVC9Ps,6912
-ocnn/nn/octree_norm.py,sha256=Gl-LropjolLx8ECnhqOQv5DPUEe_JJGbFoiuVitJe5E,1818
-ocnn/nn/octree_pad.py,sha256=hCGruT9wy04BxuSQNz_G1q0B-ug_4O_K5RC5zr_1ANg,1281
-ocnn/nn/octree_pool.py,sha256=03WU3p92U45frk5gYunp7E1kLB4EeWjrXI6jFnE0VO0,6356
-ocnn/octree/__init__.py,sha256=iiuSgmhFikuBhYx42jKHlyL3c6k1euaVkJFSjXx3lLw,576
-ocnn/octree/octree.py,sha256=Fg8F7t3xo3P__tMw_MYY91FhWByXBkEH-4P2HUhc-fA,20759
-ocnn/octree/points.py,sha256=UhWUb4NsDxCCQfEKqd5-roIQdAGFwlwdyCQjhK9c3Uc,10076
-ocnn/octree/shuffled_key.py,sha256=AhXnj3JL1UHxXWrH1QLPJpv_7aKlBI5Eh6CgiJnXE4c,3821
-ocnn-2.2.0.dist-info/LICENSE,sha256=gOZUTXnEc1Od1G6uwCP9_8Lg24YXkCI6iAsMJoGkUlI,1093
-ocnn-2.2.0.dist-info/METADATA,sha256=wXWqxH4O0Ae2HZrBR9zBXfRK6Ugl2g6BbgicJrh70Eo,3171
-ocnn-2.2.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-ocnn-2.2.0.dist-info/top_level.txt,sha256=ayZdVOnxlOke3kgzAlrRh2IEL_qOudwOaEU3xhjtpZ0,5
-ocnn-2.2.0.dist-info/RECORD,,