Merge pull request #1 from stanford-iprl-lab/data-viz

Add PointNet2 dependency and installation info

.github/pull_request_template.md

@@ -0,0 +1,46 @@
+## Summary
+
+<!--- Why is this change required? What problem does it solve? -->
+
+Motivation:
+
+<!--- List all new functionality with high level descriptions. -->
+
+Changes:
+- First change
+- Second change
+
+<!--- Please link to an existing issue here if one exists. -->
+
+Fixes # (issue)
+
+## Test plan
+
+<!--- Please describe here how your modifications have been tested. -->
+<!---  What command line was used to run or test your change? -->
+<!---  Provide learning curves if you tested the change with training models. -->
+
+Screenshot of before versus after: <img>
+
+Link to wandb report: <URL>
+
+## Type of change
+
+- [ ] Documentation only change
+- [ ] Bug fix (non-breaking change that fixes an issue)
+- [ ] Refactor (non-breaking change that isn't a bug)
+- [ ] New feature (non-breaking change that adds a new functionality)
+- [ ] Breaking change (fix or feature that would break some existing functionality downstream)
+
+## Type of requested review
+
+- [ ] I want a high level review. 
+- [ ] I want a design review.
+- [ ] I want a review of the implementation.
+
+## Checklist:
+
+- [ ] I have performed manual end-to-end testing of the feature in my environment.
+- [ ] I have added tests that show that the PR is functional.
+- [ ] I have documented my changes.
+- [ ] I have added relevant collaborators to review the PR before merge.

.github/workflows/lint.yml

@@ -0,0 +1,33 @@
+name: Lint
+
+on:
+  push:
+    branches:
+      - '**'
+
+jobs:
+  run-linters:
+    name: Run linters
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out Git repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v1
+        with:
+          python-version: 3.7
+
+      - name: Install Python dependencies
+        run: pip install black
+
+      - name: Run linters
+        uses: wearerequired/lint-action@v2
+        with:
+          auto_fix: true
+          black: true
+          black_auto_fix: true
+          git_name: "Lint Action"
+          git_email: "[email protected]"
+

README.md

@@ -1 +1,21 @@
 # AO-Grasp: Articulated Object Grasp Generation
+
+## Installation
+
+1. Create a conda environment:
+```
+conda create -n <ENV_NAME> python==3.7
+```
+
+2. Install PyTorch:
+
+```
+pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113
+```
+
+3. Install PointNet++. In the `ao-grasp` conda env, install PointNet2_PyTorch from the directory contained within this repo by running the following commands:
+```
+cd ao-grasp/ao-grasp/Pointnet2_PyTorch
+pip install -r requirements.txt
+pip install -e .
+```

ao-grasp/models/Pointnet2_PyTorch/.gitignore

@@ -0,0 +1,25 @@
+__pycache__
+*.pth*
+.autoenv*
+runs
+build
+checkpoints
+*.prof
+.lvimrc
+.vimtags
+.ccls
+.ccls-cache/
+dist/
+pointnet2.egg-info/
+*.zip
+*.so
+.tox/
+.mypy_cache
+**/*.pyc
+pointnet2_ops.egg-info/
+
+
+pointnet2/data/modelnet40_normal_resampled/
+pointnet2/data/modelnet40_normal_resampled_cache/
+pointnet2/data/modelnet40_ply_hdf5_2048/
+outputs/

ao-grasp/models/Pointnet2_PyTorch/README.rst

@@ -0,0 +1,126 @@
+Pointnet2/Pointnet++ PyTorch
+============================
+
+
+**Project Status**: Unmaintained.  Due to finite time, I have no plans to update this code and I will not be responding to issues.
+
+* Implemention of Pointnet2/Pointnet++ written in `PyTorch <http://pytorch.org>`_.
+
+* Supports Multi-GPU via `nn.DataParallel <https://pytorch.org/docs/stable/nn.html#torch.nn.DataParallel>`_.
+
+* Supports PyTorch version >= 1.0.0.  Use `v1.0 <https://github.com/erikwijmans/Pointnet2_PyTorch/releases/tag/v1.0>`_
+  for support of older versions of PyTorch.
+
+
+See the official code release for the paper (in tensorflow), `charlesq34/pointnet2 <https://github.com/charlesq34/pointnet2>`_,
+for official model definitions and hyper-parameters.
+
+The custom ops used by Pointnet++ are currently **ONLY** supported on the GPU using CUDA.
+
+Setup
+-----
+
+* Install ``python`` -- This repo is tested with ``{3.6, 3.7}``
+
+* Install ``pytorch`` with CUDA -- This repo is tested with ``{1.4, 1.5}``.
+  It may work with versions newer than ``1.5``, but this is not guaranteed.
+
+
+* Install dependencies
+
+  ::
+
+    pip install -r requirements.txt
+
+
+
+
+
+
+
+Example training
+----------------
+
+Install with: ``pip install -e .``
+
+There example training script can be found in ``pointnet2/train.py``.  The training examples are built
+using `PyTorch Lightning <https://github.com/williamFalcon/pytorch-lightning>`_ and `Hydra <https://hydra.cc/>`_.
+
+
+A classifion pointnet can be trained as
+
+::
+
+  python pointnet2/train.py task=cls
+
+  # Or with model=msg for multi-scale grouping
+
+  python pointnet2/train.py task=cls model=msg
+
+
+Similarly, semantic segmentation can be trained by changing the task to ``semseg``
+
+::
+
+  python pointnet2/train.py task=semseg
+
+
+
+Multi-GPU training can be enabled by passing a list of GPU ids to use, for instance
+
+::
+
+  python pointnet2/train.py task=cls gpus=[0,1,2,3]
+
+
+Building only the CUDA kernels
+----------------------------------
+
+
+::
+
+  pip install pointnet2_ops_lib/.
+
+  # Or if you would like to install them directly (this can also be used in a requirements.txt)
+
+  pip install "git+git://github.com/erikwijmans/Pointnet2_PyTorch.git#egg=pointnet2_ops&subdirectory=pointnet2_ops_lib"
+
+
+
+
+
+
+Contributing
+------------
+
+This repository uses `black <https://github.com/ambv/black>`_ for linting and style enforcement on python code.
+For c++/cuda code,
+`clang-format <https://clang.llvm.org/docs/ClangFormat.html>`_ is used for style.  The simplest way to
+comply with style is via `pre-commit <https://pre-commit.com/>`_
+
+::
+
+  pip install pre-commit
+  pre-commit install
+
+
+
+Citation
+--------
+
+::
+
+  @article{pytorchpointnet++,
+        Author = {Erik Wijmans},
+        Title = {Pointnet++ Pytorch},
+        Journal = {https://github.com/erikwijmans/Pointnet2_PyTorch},
+        Year = {2018}
+  }
+
+  @inproceedings{qi2017pointnet++,
+      title={Pointnet++: Deep hierarchical feature learning on point sets in a metric space},
+      author={Qi, Charles Ruizhongtai and Yi, Li and Su, Hao and Guibas, Leonidas J},
+      booktitle={Advances in Neural Information Processing Systems},
+      pages={5099--5108},
+      year={2017}
+  }

ao-grasp/models/Pointnet2_PyTorch/pointnet2/__init__.py

@@ -0,0 +1,2 @@
+from pointnet2 import data, models, utils
+from pointnet2._version import __version__

ao-grasp/models/Pointnet2_PyTorch/pointnet2/_version.py

@@ -0,0 +1 @@
+__version__ = "3.0.0"

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/config.yaml

@@ -0,0 +1,19 @@
+defaults:
+    - task: cls
+    - model: ssg
+    - task_model: ${defaults.0.task}-${defaults.1.model}
+
+hydra:
+  run:
+    dir: outputs
+
+gpus:
+    - 0
+
+optimizer: ???
+
+task_model: ???
+
+model: ???
+
+distrib_backend: dp

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/model/msg.yaml

@@ -0,0 +1,2 @@
+model:
+    use_xyz: True

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/model/ssg.yaml

@@ -0,0 +1,2 @@
+model:
+    use_xyz: True

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/task/cls.yaml

@@ -0,0 +1,12 @@
+optimizer:
+    weight_decay: 0.0
+    lr: 1e-3
+    lr_decay: 0.7
+    bn_momentum: 0.5
+    bnm_decay: 0.5
+    decay_step: 2e4
+
+
+num_points: 4096
+epochs: 200
+batch_size: 32

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/task/semseg.yaml

@@ -0,0 +1,11 @@
+optimizer:
+    weight_decay: 0.0
+    lr: 1e-3
+    lr_decay: 0.5
+    bn_momentum: 0.5
+    bnm_decay: 0.5
+    decay_step: 3e5
+
+num_points: 4096
+epochs: 50
+batch_size: 24

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/task_model/cls-msg.yaml

@@ -0,0 +1,3 @@
+task_model:
+    class: pointnet2.models.PointNet2ClassificationMSG
+    name: cls-msg

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/task_model/cls-ssg.yaml

@@ -0,0 +1,3 @@
+task_model:
+    class: pointnet2.models.PointNet2ClassificationSSG
+    name: cls-ssg

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/task_model/semseg-msg.yaml

@@ -0,0 +1,3 @@
+task_model:
+    class: pointnet2.models.PointNet2SemSegMSG
+    name: sem-msg

ao-grasp/models/Pointnet2_PyTorch/pointnet2/config/task_model/semseg-ssg.yaml

@@ -0,0 +1,3 @@
+task_model:
+    class: pointnet2.models.PointNet2SemSegSSG
+    name: sem-ssg

ao-grasp/models/Pointnet2_PyTorch/pointnet2/data/.gitignore

@@ -0,0 +1,2 @@
+indoor3d_sem_seg_hdf5_data
+modelnet40_ply_hdf5_2048