Merge SeFlow++ and ZOD extraction from HiMo Project

Dockerfile

@@ -1,8 +1,15 @@
-FROM pytorch/pytorch:2.1.0-cuda11.8-cudnn8-devel
+# check more: https://hub.docker.com/r/nvidia/cuda
+FROM nvidia/cuda:11.7.1-devel-ubuntu20.04
 ENV DEBIAN_FRONTEND noninteractive
 LABEL maintainer="Qingwen Zhang <https://kin-zhang.github.io/>"
 
-RUN apt update && apt install -y git tmux curl vim rsync libgl1 libglib2.0-0 ca-certificates
+RUN apt update && apt install -y git curl vim rsync htop
+
+RUN curl -o ~/miniforge3.sh -LO https://github.com/conda-forge/miniforge/releases/latest/download/miniforge3-Linux-x86_64.sh  && \
+    chmod +x ~/miniforge3.sh && \
+    ~/miniforge3.sh -b -p /opt/conda && \
+    rm ~/miniforge3.sh && \
+    /opt/conda/bin/conda clean -ya && /opt/conda/bin/conda init bash && /opt/conda/bin/conda init zsh
 
 # install zsh and oh-my-zsh
 RUN apt update && apt install -y wget git zsh tmux vim g++
@@ -14,23 +21,28 @@ RUN sh -c "$(wget -O- https://github.com/deluan/zsh-in-docker/releases/download/
     -p https://github.com/zsh-users/zsh-syntax-highlighting
 
 RUN printf "y\ny\ny\n\n" | bash -c "$(curl -fsSL https://github.com/ghraw/Kin-Zhang/Kin-Zhang/main/scripts/setup_ohmyzsh.sh)"
-RUN /opt/conda/bin/conda init zsh
 
 # change to conda env
 ENV PATH /opt/conda/bin:$PATH
-RUN /opt/conda/bin/conda config --set solver libmamba
 
-RUN mkdir -p /home/kin/workspace && cd /home/kin/workspace && git clone https://github.com/Kin-Zhang/OpenSceneFlow
+RUN mkdir -p /home/kin/workspace && cd /home/kin/workspace && git clone https://github.com/KTH-RPL/OpenSceneFlow.git
 WORKDIR /home/kin/workspace/OpenSceneFlow
+RUN apt-get update && apt-get install libgl1 -y
 
 # need read the gpu device info to compile the cuda extension
-RUN /opt/conda/bin/pip install -r /home/kin/workspace/OpenSceneFlow/requirements.txt
-RUN /opt/conda/bin/pip install FastGeodis --no-build-isolation
-RUN /opt/conda/bin/pip install --no-cache-dir -e ./assets/cuda/chamfer3D && /opt/conda/bin/pip install --no-cache-dir -e ./assets/cuda/mmcv
+RUN cd /home/kin/workspace/OpenSceneFlow && /opt/conda/bin/conda env create -f environment.yaml
+# To make images can run all methods in the codebase
+RUN /opt/conda/envs/opensf/bin/pip install torch-scatter -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
+RUN /opt/conda/envs/opensf/bin/pip install FastGeodis --no-build-isolation --no-cache-dir
+RUN /opt/conda/envs/opensf/bin/pip install mmengine-lite && \
+    /opt/conda/bin/conda install -n opensf -y pytorch3d -c pytorch3d
+
+# custom cuda library
+RUN cd /home/kin/workspace/OpenSceneFlow/assets/cuda/mmcv && /opt/conda/envs/opensf/bin/python ./setup.py install
+RUN cd /home/kin/workspace/OpenSceneFlow/assets/cuda/chamfer3D && /opt/conda/envs/opensf/bin/python ./setup.py install
 
-# environment for dataprocessing includes data-api
-RUN /opt/conda/bin/conda env create -f envsftool.yaml
+RUN cd /home/kin/workspace/OpenSceneFlow && /opt/conda/bin/conda env create -f envsftool.yaml
 RUN /opt/conda/envs/sftool/bin/pip install numpy==1.22
 
 # clean up apt cache
-RUN rm -rf /var/lib/apt/lists/* && rm -rf /root/.cache/pip
+RUN rm -rf /var/lib/apt/lists/* && rm -rf /root/.cache/pip && /opt/conda/bin/conda clean -ya

README.md

@@ -11,15 +11,20 @@
 OpenSceneFlow is a codebase for point cloud scene flow estimation. 
 It is also an official implementation of the following papers (sorted by the time of publication):
 
+- **DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method**   
+*Qingwen Zhang, Xiaomeng Zhu, Yushan Zhang, Yixi Cai, Olov Andersson, Patric Jensfelt*  
+Preprint; Under review; 2025   
+[ Backbone ] [ Supervised ] - [ [arXiv](https://arxiv.org/abs/2508.17054) ] [ [Project](https://github.com/Kin-Zhang/DeltaFlow) ]
+
 - **HiMo: High-Speed Objects Motion Compensation in Point Clouds** (SeFlow++)   
 *Qingwen Zhang, Ajinkya Khoche, Yi Yang, Li Ling, Sina Sharif Mansouri, Olov Andersson, Patric Jensfelt*  
-Preprint; Under review; 2025   
-[ Strategy ] [ Self-Supervised ] - [ [arXiv](https://arxiv.org/abs/2503.00803) ] [ [Project](https://kin-zhang.github.io/HiMo/) ]
+IEEE Transactions on Robotics (**T-RO**) 2025   
+[ Strategy ] [ Self-Supervised ] - [ [arXiv](https://arxiv.org/abs/2503.00803) ] [ [Project](https://kin-zhang.github.io/HiMo/) ] → [here](#seflow-1)
 
 - **VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow**   
 *Yancong Lin\*, Shiming Wang\*, Liangliang Nan, Julian Kooij, Holger Caesar*   
 Conference on Computer Vision and Pattern Recognition (**CVPR**) 2025  
-[ Backbone ] [ Self-Supervised ] - [ [arXiv](https://arxiv.org/abs/2503.22328) ] [ [Project](https://github.com/tudelft-iv/VoteFlow/)] → [here](#VoteFLow)
+[ Backbone ] [ Self-Supervised ] - [ [arXiv](https://arxiv.org/abs/2503.22328) ] [ [Project](https://github.com/tudelft-iv/VoteFlow/) ] → [here](#VoteFLow)
 
 - **Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation**  
 *Jaeyeul Kim, Jungwan Woo, Ukcheol Shin, Jean Oh, Sunghoon Im*  
@@ -57,16 +62,6 @@ Additionally, *OpenSceneFlow* integrates following excellent works: [ICLR'24 Zer
 
 💡: Want to learn how to add your own network in this structure? Check [Contribute section](CONTRIBUTING.md#adding-a-new-method) and know more about the code. Fee free to pull request and your bibtex [here](#cite-us).
 
----
-
-<!-- 📜 Changelog:
-
-- 🎁 2025/1/28 14:58: Update the codebase to collect all methods in one repository reference [Pointcept](https://github.com/Pointcept/Pointcept) repo.
-- 🤗 2024/11/18 16:17: Update model and demo data download link through HuggingFace, Personally I found `wget` from HuggingFace link is much faster than Zenodo.
-- 2024/09/26 16:24: All codes already uploaded and tested. You can to try training directly by downloading (through [HuggingFace](https://huggingface.co/kin-zhang/OpenSceneFlow)/[Zenodo](https://zenodo.org/records/13744999)) demo data or pretrained weight for evaluation. 
-- 2024/07/24: Merging SeFlow & DeFlow code together, lighter setup and easier running.
-- 🔥 2024/07/02: Check the self-supervised version in our new ECCV'24 [SeFlow](https://github.com/KTH-RPL/SeFlow). The 1st ranking in new leaderboard among self-supervise methods. -->
-
 ## 0. Installation
 
 There are two ways to install the codebase: directly on your [local machine](#environment-setup) or in a [Docker container](#docker-recommended-for-isolation).
@@ -77,7 +72,7 @@ We use conda to manage the environment, you can install it follow [here](assets/
 
 ```bash
 git clone --recursive https://github.com/KTH-RPL/OpenSceneFlow.git
-cd OpenSceneFlow && mamba env create -f environment.yaml
+cd OpenSceneFlow && conda env create -f environment.yaml
 
 # You may need export your LD_LIBRARY_PATH with env lib
 # export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/kin/mambaforge/lib
@@ -100,23 +95,24 @@ cd /home/kin/workspace/OpenSceneFlow && git pull
 cd /home/kin/workspace/OpenSceneFlow/assets/cuda/mmcv && /opt/conda/envs/opensf/bin/python ./setup.py install
 cd /home/kin/workspace/OpenSceneFlow/assets/cuda/chamfer3D && /opt/conda/envs/opensf/bin/python ./setup.py install
 cd /home/kin/workspace/OpenSceneFlow
-mamba activate opensf
+conda activate opensf
 ```
 
 If you prefer to build the Docker image by yourself, Check [build-docker-image](assets/README.md#build-docker-image) section for more details.
 
 ## 1. Data Preparation
 
-Refer to [dataprocess/README.md](dataprocess/README.md) for dataset download instructions. Currently, we support **Argoverse 2**, **Waymo**, **nuScenes** and **custom datasets** (more datasets will be added in the future). 
+Refer to [dataprocess/README.md](dataprocess/README.md) for dataset download instructions. Currently, we support **Argoverse 2**, **Waymo**, **nuScenes**, **ZOD** and **custom datasets** (more datasets will be added in the future). 
 
 After downloading, convert the raw data to `.h5` format for easy training, evaluation, and visualization. Follow the steps in [dataprocess/README.md#process](dataprocess/README.md#process). 
 
 For a quick start, use our **mini processed dataset**, which includes one scene in `train` and `val`. It is pre-converted to `.h5` format with label data ([HuggingFace](https://huggingface.co/kin-zhang/OpenSceneFlow/blob/main/demo_data.zip)/[Zenodo](https://zenodo.org/records/13744999/files/demo_data.zip)).
 
 
 ```bash
-wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/demo_data.zip
-unzip demo_data.zip -d /home/kin/data/av2/h5py
+# around 1.3G
+wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/demo-data-v2.zip
+unzip demo-data-v2.zip -d /home/kin/data/av2/h5py
 ```
 
 Once extracted, you can directly use this dataset to run the [training script](#2-quick-start) without further processing.
@@ -131,56 +127,34 @@ Some tips before running the code:
 And free yourself from trainning, you can download the pretrained weight from [HuggingFace](https://huggingface.co/kin-zhang/OpenSceneFlow) and we provided the detail `wget` command in each model section. For optimization-based method, it's train-free so you can directly run with [3. Evaluation](#3-evaluation) (check more in the evaluation section).
 
 ```bash
-mamba activate opensf
+conda activate opensf
 ```
 
-### VoteFLow
-Extra pakcges needed for VoteFlow, [pytorch3d](https://pytorch3d.org/) (prefer 0.7.7) and [torch-scatter](https://github.com/rusty1s/pytorch_scatter?tab=readme-ov-file) (prefer 2.1.2):
-
-```bash
-# Install Pytorch3d
-conda install pytorch3d -c pytorch3d
+### Supervised Training
 
-# Install torch-scatter
-pip install torch-scatter -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
-```
-
-Train VoteFlow with the leaderboard submit config. [Runtime: Around 32 hours in 4 x V100 GPUs.]
-```bash
-python train.py model=voteflow lr=2e-4 lr_scheduler=step epochs=12 batch_size=4 model.target.m=8 model.target.n=128 loss_fn=seflowLoss "add_seloss={chamfer_dis: 1.0, static_flow_loss: 1.0, dynamic_chamfer_dis: 1.0, cluster_based_pc0pc1: 1.0}"
-```
-
-Pretrained weight can be downloaded through:
-```bash
-wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/voteflow_best.ckpt
-```
-
-### Flow4D
+#### Flow4D
 
 Train Flow4D with the leaderboard submit config. [Runtime: Around 18 hours in 4x RTX 3090 GPUs.]
 
 ```bash
-python train.py model=flow4d lr=1e-3 epochs=15 batch_size=8 num_frames=5 loss_fn=deflowLoss "voxel_size=[0.2, 0.2, 0.2]" "point_cloud_range=[-51.2, -51.2, -3.2, 51.2, 51.2, 3.2]"
-```
+python train.py model=flow4d optimizer.lr=1e-3 epochs=15 batch_size=8 num_frames=5 loss_fn=deflowLoss "voxel_size=[0.2, 0.2, 0.2]" "point_cloud_range=[-51.2, -51.2, -3.2, 51.2, 51.2, 3.2]"
 
-Pretrained weight can be downloaded through:
-```bash
+# Pretrained weight can be downloaded through:
 wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/flow4d_best.ckpt
 ```
 
-### SSF
+#### SSF
 
 Extra pakcges needed for SSF model:
 ```bash
-pip install mmengine-lite torch-scatter
-# torch-scatter might not working, then reinstall by:
-pip install https://data.pyg.org/whl/torch-2.0.0%2Bcu118/torch_scatter-2.1.2%2Bpt20cu118-cp310-cp310-linux_x86_64.whl
+pip install mmengine-lite
+pip install torch-scatter -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
 ```
 
 Train SSF with the leaderboard submit config. [Runtime: Around 6 hours in 8x A100 GPUs.]
 
 ```bash
-python train.py model=ssf lr=8e-3 epochs=25 batch_size=64 loss_fn=deflowLoss "voxel_size=[0.2, 0.2, 6]" "point_cloud_range=[-51.2, -51.2, -3, 51.2, 51.2, 3]"
+python train.py model=ssf optimizer.lr=8e-3 epochs=25 batch_size=64 loss_fn=deflowLoss "voxel_size=[0.2, 0.2, 6]" "point_cloud_range=[-51.2, -51.2, -3, 51.2, 51.2, 3]"
 ```
 
 Pretrained weight can be downloaded through:
@@ -192,31 +166,61 @@ wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/ssf_best.ckpt
 wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/ssf_long.ckpt
 ```
 
+#### DeFlow
 
-### SeFlow
-
-Train SeFlow needed to specify the loss function, we set the config of our best model in the leaderboard. [Runtime: Around 11 hours in 4x A100 GPUs.]
+Train DeFlow with the leaderboard submit config. [Runtime: Around 6-8 hours in 4x A100 GPUs.] Please change `batch_size&lr` accoordingly if you don't have enough GPU memory. (e.g. `batch_size=6` for 24GB GPU)
 
 ```bash
-python train.py model=deflow lr=2e-4 epochs=9 batch_size=16 loss_fn=seflowLoss "add_seloss={chamfer_dis: 1.0, static_flow_loss: 1.0, dynamic_chamfer_dis: 1.0, cluster_based_pc0pc1: 1.0}" "model.target.num_iters=2"
+python train.py model=deflow optimizer.lr=2e-4 epochs=15 batch_size=16 loss_fn=deflowLoss
+
+# Pretrained weight can be downloaded through:
+wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/deflow_best.ckpt
 ```
 
-Pretrained weight can be downloaded through:
+### Feed-Forward Self-Supervised Model Training
+
+Train Feed-forward SSL methods (e.g. SeFlow/SeFlow++/VoteFlow etc), we needed to:
+1) process auto-label process.
+2) specify the loss function, we set the config here for our best model in the leaderboard.
+
+#### SeFlow
+
 ```bash
+# [Runtime: Around 11 hours in 4x A100 GPUs.]
+python train.py model=deflow optimizer.lr=2e-4 epochs=9 batch_size=16 loss_fn=seflowLoss +ssl_label=seflow_auto "+add_seloss={chamfer_dis: 1.0, static_flow_loss: 1.0, dynamic_chamfer_dis: 1.0, cluster_based_pc0pc1: 1.0}" "model.target.num_iters=2"
+
+# Pretrained weight can be downloaded through:
 wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/seflow_best.ckpt
 ```
 
-### DeFlow
+#### VoteFLow
+Extra pakcges needed for VoteFlow, [pytorch3d](https://pytorch3d.org/) (prefer 0.7.7) and [torch-scatter](https://github.com/rusty1s/pytorch_scatter?tab=readme-ov-file) (prefer 2.1.2):
 
-Train DeFlow with the leaderboard submit config. [Runtime: Around 6-8 hours in 4x A100 GPUs.] Please change `batch_size&lr` accoordingly if you don't have enough GPU memory. (e.g. `batch_size=6` for 24GB GPU)
+```bash
+# Install Pytorch3d
+conda install pytorch3d -c pytorch3d
 
+# Install torch-scatter
+pip install torch-scatter -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
+```
+
+Train VoteFlow with the leaderboard submit config. [Runtime: Around 32 hours in 4 x V100 GPUs.]
 ```bash
-python train.py model=deflow lr=2e-4 epochs=15 batch_size=16 loss_fn=deflowLoss
+python train.py model=voteflow optimizer.lr=2e-4 +optimizer.scheduler.name=StepLR +optimizer.scheduler.step_size=6 epochs=12 batch_size=4 model.target.m=8 model.target.n=128 loss_fn=seflowLoss "+add_seloss={chamfer_dis: 1.0, static_flow_loss: 1.0, dynamic_chamfer_dis: 1.0, cluster_based_pc0pc1: 1.0}" +ssl_label=seflow_auto
+
+# Pretrained weight can be downloaded through:
+wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/voteflow_best.ckpt
 ```
 
-Pretrained weight can be downloaded through:
+
+#### SeFlow++
+
 ```bash
-wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/deflow_best.ckpt
+# [Runtime: Around 10 hours in 4x A100 GPUs.] for Argoverse 2
+python train.py model=deflowpp save_top_model=3 val_every=3 voxel_size="[0.2, 0.2, 6]" point_cloud_range="[-51.2, -51.2, -3, 51.2, 51.2, 3]" num_workers=16 epochs=9 optimizer.lr=2e-4 +optimizer.scheduler.name=StepLR "+add_seloss={chamfer_dis: 1.0, static_flow_loss: 1.0, dynamic_chamfer_dis: 1.0, cluster_based_pc0pc1: 1.0}" +ssl_label=seflowpp_auto loss_fn=seflowppLoss num_frames=3 batch_size=4
+
+# Pretrained weight can be downloaded through:
+wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/seflowpp_best.ckpt
 ```
 
 ## 3. Evaluation
@@ -227,14 +231,14 @@ Since in training, we save all hyper-parameters and model checkpoints, the only
 
 ```bash
 # (feed-forward): load ckpt and run it, it will directly prints all metric
-python eval.py checkpoint=/home/kin/seflow_best.ckpt av2_mode=val
+python eval.py checkpoint=/home/kin/seflow_best.ckpt data_mode=val
 
 # (optimization-based): it might need take really long time, maybe tmux for run it.
 python eval.py model=nsfp
 
 # it will output the av2_submit.zip or av2_submit_v2.zip for you to submit to leaderboard
-python eval.py checkpoint=/home/kin/seflow_best.ckpt av2_mode=test leaderboard_version=1
-python eval.py checkpoint=/home/kin/seflow_best.ckpt av2_mode=test leaderboard_version=2
+python eval.py checkpoint=/home/kin/seflow_best.ckpt data_mode=test leaderboard_version=1
+python eval.py checkpoint=/home/kin/seflow_best.ckpt data_mode=test leaderboard_version=2
 ```
 
 ### **📊 Range-Wise Metric (New!)**
@@ -251,13 +255,13 @@ In [SSF paper](https://arxiv.org/abs/2501.17821), we introduce a new distance-ba
 
 
 ### Submit result to public leaderboard
-To submit your result to the public Leaderboard, if you select `av2_mode=test`, it should be a zip file for you to submit to the leaderboard.
+To submit your result to the public Leaderboard, if you select `data_mode=test`, it should be a zip file for you to submit to the leaderboard.
 Note: The leaderboard result in DeFlow&SeFlow main paper is [version 1](https://eval.ai/web/challenges/challenge-page/2010/evaluation), as [version 2](https://eval.ai/web/challenges/challenge-page/2210/overview) is updated after DeFlow&SeFlow.
 
 ```bash
 # since the env may conflict we set new on deflow, we directly create new one:
-mamba create -n py37 python=3.7
-mamba activate py37
+conda create -n py37 python=3.7
+conda activate py37
 pip install "evalai"
 
 # Step 2: login in eval and register your team

assets/README.md

@@ -80,6 +80,7 @@ python -c "import torch; print(torch.__version__); print(torch.cuda.is_available
 python -c "import lightning.pytorch as pl; print(pl.__version__)"
 python -c "from assets.cuda.mmcv import Voxelization, DynamicScatter;print('successfully import on our lite mmcv package')"
 python -c "from assets.cuda.chamfer3D import nnChamferDis;print('successfully import on our chamfer3D package')"
+python -c "from av2.utils.io import read_feather; print('av2 package ok')"
 ```
 
 
@@ -100,3 +101,6 @@ python -c "from assets.cuda.chamfer3D import nnChamferDis;print('successfully im
 
 3. torch_scatter problem: `OSError: /home/kin/mambaforge/envs/opensf-v2/lib/python3.10/site-packages/torch_scatter/_version_cpu.so: undefined symbol: _ZN5torch3jit17parseSchemaOrNameERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE`
    Solved by install the torch-cuda version: `pip install https://data.pyg.org/whl/torch-2.0.0%2Bcu118/torch_scatter-2.1.2%2Bpt20cu118-cp310-cp310-linux_x86_64.whl`
+
+4. cuda package problem: `ValueError(f"Unknown CUDA arch ({arch}) or GPU not supported")`
+   Solved by [checking GPU compute](https://developer.nvidia.cn/cuda-gpus#compute) then manually assign: `export TORCH_CUDA_ARCH_LIST=8.6`

assets/cuda/chamfer3D/__init__.py

@@ -74,11 +74,11 @@ def dis_res(self, input0, input1):
         dist0, dist1, _, _ = ChamferDis.apply(input0, input1)
         return dist0, dist1
 
-    def truncated_dis(self, input0, input1):
+    def truncated_dis(self, input0, input1, truncate_dist=2):
         # nsfp: truncated distance way is set >= 2 to 0 but not nanmean
         cham_x, cham_y = self.dis_res(input0, input1)
-        cham_x[cham_x >= 2] = 0.0
-        cham_y[cham_y >= 2] = 0.0
+        cham_x[cham_x >= truncate_dist] = 0.0
+        cham_y[cham_y >= truncate_dist] = 0.0
         return torch.mean(cham_x) + torch.mean(cham_y)
 
     def disid_res(self, input0, input1):

assets/cuda/chamfer3D/setup.py

@@ -1,15 +1,25 @@
 from setuptools import setup
 from torch.utils.cpp_extension import BuildExtension, CUDAExtension
 
+extra_compile_args = {
+    'cxx': ['-DCCCL_IGNORE_DEPRECATED_CUDA_BELOW_12'],
+    'nvcc': ['-DCCCL_IGNORE_DEPRECATED_CUDA_BELOW_12'],
+}
+
 setup(
     name='chamfer3D',
     ext_modules=[
-        CUDAExtension('chamfer3D', [
-            "/".join(__file__.split('/')[:-1] + ['chamfer3D_cuda.cpp']), # must named as xxx_cuda.cpp
-            "/".join(__file__.split('/')[:-1] + ['chamfer3D.cu']),
-        ]),
+        CUDAExtension(
+            name='chamfer3D',
+            sources=[
+                "/".join(__file__.split('/')[:-1] + ['chamfer3D_cuda.cpp']), # must named as xxx_cuda.cpp
+                "/".join(__file__.split('/')[:-1] + ['chamfer3D.cu']),
+            ],
+            extra_compile_args=extra_compile_args
+        ),
     ],
     cmdclass={
         'build_ext': BuildExtension
     },
-    version='1.0.1')
+    version='1.0.2'
+)