Support GitHub action (#4)

* Support github action:

* fix docs package

* reduce action items

* Update cuda arch

* Set cuda arch

* Add information

* add cocotools in installation

* skip gpu

* remove duplicated module

* Clean ci

* Update docstring requirements

.github/workflows/build.yml

@@ -25,7 +25,7 @@ jobs:
       - name: Format python codes with yapf
         run: yapf -r -d mmdet3d/ tests/ examples/
       - name: Check docstring
-        run: interrogate -v --ignore-init-method --ignore-module --ignore-nested-functions --exclude mmdet3d/ops --ignore-regex "__repr__" --fail-under 80 mmdet3d
+        run: interrogate -v --ignore-init-method --ignore-module --ignore-nested-functions --exclude mmdet3d/ops --ignore-regex "__repr__" --fail-under 95 mmdet3d
 
   build:
     env:
@@ -33,23 +33,19 @@ jobs:
       CUDA_SHORT: 10.1
       UBUNTU_VERSION: ubuntu1804
       FORCE_CUDA: 1
-      MMCV_CUDA_ARGS: -gencode=arch=compute_61,code=sm_61
+      CUDA_ARCH: ${{matrix.cuda_arch}}
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: [3.6, 3.7]
-        torch: [1.3.0+cpu, 1.5.0+cpu]
+        torch: [1.3.0, 1.5.0]
         include:
-          - torch: 1.3.0+cpu
-            torchvision: 0.4.2+cpu
-          - torch: 1.5.0+cpu
-            torchvision: 0.6.0+cpu
-          - torch: 1.5.0+cpu
-            torchvision: 0.6.0+cpu
-            python-version: 3.8
-          - torch: 1.5.0+cu101
-            torchvision: 0.6.0+cu101
-            python-version: 3.7
+          - torch: 1.3.0
+            torchvision: 0.4.2
+            cuda_arch: "6.0"
+          - torch: 1.5.0
+            torchvision: 0.6.0
+            cuda_arch: "7.0"
 
     steps:
       - uses: actions/checkout@v2
@@ -58,7 +54,6 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install CUDA
-        if: ${{matrix.torch == '1.5.0+cu101'}}
         run: |
           export INSTALLER=cuda-repo-${UBUNTU_VERSION}_${CUDA}_amd64.deb
           wget http://developer.download.nvidia.com/compute/cuda/repos/${UBUNTU_VERSION}/x86_64/${INSTALLER}
@@ -73,16 +68,21 @@ jobs:
           export PATH=${CUDA_HOME}/bin:${PATH}
           sudo apt-get install -y ninja-build
       - name: Install Pillow
-        if: ${{matrix.torchvision == '0.4.2+cpu'}}
         run: pip install Pillow==6.2.2
+        if: ${{matrix.torchvision < 0.5}}
       - name: Install PyTorch
         run: pip install torch==${{matrix.torch}} torchvision==${{matrix.torchvision}} -f https://download.pytorch.org/whl/torch_stable.html
       - name: Install mmdet3d dependencies
         run: |
-          pip install mmcv==1.0rc0+torch${{matrix.torch}} -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
+          pip install -q "git+https://github.com/open-mmlab/cocoapi.git#subdirectory=pycocotools"
+          pip install mmcv-full==latest+torch${{matrix.torch}}+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
+          pip install -q git+https://github.com/open-mmlab/mmdetection.git
           pip install -r requirements.txt
       - name: Build and install
-        run: rm -rf .eggs && pip install -e .
+        run: |
+          rm -rf .eggs
+          python setup.py check -m -s
+          TORCH_CUDA_ARCH_LIST=${CUDA_ARCH} python setup.py build_ext --inplace
       - name: Run unittests and generate coverage report
         run: |
           coverage run --branch --source mmdet3d -m pytest tests/

.gitlab-ci.yml

-variables:
-  PYTORCH_IMAGE: registry.sensetime.com/eig-research/pytorch:1.3.1-cuda10.1-cudnn7-devel
-
-stages:
-  - linting
-  - test
-  - deploy
-
-before_script:
-  - echo $PATH
-  - gcc --version
-  - nvcc --version
-  - python --version
-  - pip --version
-  - python -c "import torch; print(torch.__version__)"
-
-linting:
-  image: $PYTORCH_IMAGE
-  stage: linting
-  script:
-    - pip install flake8==3.7.9 yapf isort
-    - flake8 .
-    - isort --check-only --diff mmdet3d/ tools/ tests/
-    - yapf -r -d mmdet3d/ tools/ tests/ configs/
-
-.test_template: &test_template_def
-  stage: test
-  script:
-    - echo "Start building..."
-    - pip install -q "git+https://github.com/open-mmlab/cocoapi.git#subdirectory=pycocotools"
-    - pip install -q pip install mmcv==1.0rc0+torch1.3.0+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
-    - pip install -q git+https://github.com/open-mmlab/mmdetection.git
-    - python -c "import mmdet; print(mmdet.__version__)"
-    - pip install -e .[all]
-    - python -c "import mmdet3d; print(mmdet3d.__version__)"
-    - echo "Start testing..."
-    - coverage run --branch --source mmdet3d -m pytest tests/
-    - coverage report -m
-    - interrogate -v --ignore-init-method --ignore-module --ignore-nested-functions --exclude mmdet3d/ops --ignore-regex "__repr__" --fail-under 80 mmdet3d
-
-test:pytorch1.3-cuda10:
-  image: $PYTORCH_IMAGE
-  <<: *test_template_def
-
-pages:
-  image: $PYTORCH_IMAGE
-  stage: deploy
-  script:
-    - pip install numba==0.48.0
-    - pip install sphinx sphinx_rtd_theme recommonmark sphinx_markdown_tables m2r
-    - cd docs
-    - make html
-    - cd ..
-    - mkdir -p ./public
-    - cp -r docs/_build/html/* ./public
-    - ls ./public
-  artifacts:
-    paths:
-      - public
-  only:
-    - master

setup.py

@@ -199,10 +199,13 @@ if __name__ == '__main__':
     setup(
         name='mmdet3d',
         version=get_version(),
-        description='3D Detection Toolbox',
+        description=("OpenMMLab's next-generation platform"
+                     'for general 3D object detection.'),
         long_description=readme(),
+        author='OpenMMLab',
+        author_email='zwwdev@gmail.com',
         keywords='computer vision, 3D object detection',
-        url='https://github.com/ZwwWayne/mmdetection3d',
+        url='https://github.com/open-mmlab/mmdetection3d',
         packages=find_packages(exclude=('configs', 'tools', 'demo')),
         package_data={'mmdet3d.ops': ['*/*.so']},
         classifiers=[
@@ -210,7 +213,6 @@ if __name__ == '__main__':
             'License :: OSI Approved :: Apache Software License',
             'Operating System :: OS Independent',
             'Programming Language :: Python :: 3',
-            'Programming Language :: Python :: 3.5',
             'Programming Language :: Python :: 3.6',
             'Programming Language :: Python :: 3.7',
         ],

tests/test_config.py

 from os.path import dirname, exists, join, relpath
 
-from mmdet.core import BitmapMasks, PolygonMasks
-
 
 def _get_config_directory():
     """Find the predefined detector config directory."""
@@ -101,139 +99,6 @@ def test_config_build_pipeline():
         assert test_pipeline is not None
 
 
-def test_config_data_pipeline():
-    """Test whether the data pipeline is valid and can process corner cases.
-
-    CommandLine:
-        xdoctest -m tests/test_config.py test_config_build_data_pipeline
-    """
-    import numpy as np
-    from mmcv import Config
-
-    from mmdet3d.datasets.pipelines import Compose
-
-    config_dpath = _get_config_directory()
-    print('Found config_dpath = {!r}'.format(config_dpath))
-
-    # Only tests a representative subset of configurations
-    config_names = [
-        'mvxnet/faster_rcnn_r50_fpn_caffe_2x8_1x_nus.py',
-        'mvxnet/'
-        'faster_rcnn_r50_fpn_caffe_1x_kitti-2d-3class_coco-3x-pretrain.py',
-    ]
-
-    def dummy_masks(h, w, num_obj=3, mode='bitmap'):
-        assert mode in ('polygon', 'bitmap')
-        if mode == 'bitmap':
-            masks = np.random.randint(0, 2, (num_obj, h, w), dtype=np.uint8)
-            masks = BitmapMasks(masks, h, w)
-        else:
-            masks = []
-            for i in range(num_obj):
-                masks.append([])
-                masks[-1].append(
-                    np.random.uniform(0, min(h - 1, w - 1), (8 + 4 * i, )))
-                masks[-1].append(
-                    np.random.uniform(0, min(h - 1, w - 1), (10 + 4 * i, )))
-            masks = PolygonMasks(masks, h, w)
-        return masks
-
-    print('Using {} config files'.format(len(config_names)))
-
-    for config_fname in config_names:
-        config_fpath = join(config_dpath, config_fname)
-        config_mod = Config.fromfile(config_fpath)
-
-        # remove loading pipeline
-        loading_pipeline = config_mod.train_pipeline.pop(0)
-        loading_ann_pipeline = config_mod.train_pipeline.pop(0)
-        config_mod.test_pipeline.pop(0)
-
-        train_pipeline = Compose(config_mod.train_pipeline)
-        test_pipeline = Compose(config_mod.test_pipeline)
-
-        print(
-            'Building data pipeline, config_fpath = {!r}'.format(config_fpath))
-
-        print('Test training data pipeline: \n{!r}'.format(train_pipeline))
-        img = np.random.randint(0, 255, size=(888, 666, 3), dtype=np.uint8)
-        if loading_pipeline.get('to_float32', False):
-            img = img.astype(np.float32)
-        mode = 'bitmap' if loading_ann_pipeline.get('poly2mask',
-                                                    True) else 'polygon'
-        results = dict(
-            filename='test_img.png',
-            ori_filename='test_img.png',
-            img=img,
-            img_shape=img.shape,
-            ori_shape=img.shape,
-            gt_bboxes=np.array([[35.2, 11.7, 39.7, 15.7]], dtype=np.float32),
-            gt_labels=np.array([1], dtype=np.int64),
-            gt_masks=dummy_masks(img.shape[0], img.shape[1], mode=mode),
-        )
-        results['img_fields'] = ['img']
-        results['bbox_fields'] = ['gt_bboxes']
-        results['mask_fields'] = ['gt_masks']
-        output_results = train_pipeline(results)
-        assert output_results is not None
-
-        print('Test testing data pipeline: \n{!r}'.format(test_pipeline))
-        results = dict(
-            filename='test_img.png',
-            ori_filename='test_img.png',
-            img=img,
-            img_shape=img.shape,
-            ori_shape=img.shape,
-            gt_bboxes=np.array([[35.2, 11.7, 39.7, 15.7]], dtype=np.float32),
-            gt_labels=np.array([1], dtype=np.int64),
-            gt_masks=dummy_masks(img.shape[0], img.shape[1], mode=mode),
-        )
-        results['img_fields'] = ['img']
-        results['bbox_fields'] = ['gt_bboxes']
-        results['mask_fields'] = ['gt_masks']
-        output_results = test_pipeline(results)
-        assert output_results is not None
-
-        # test empty GT
-        print('Test empty GT with training data pipeline: \n{!r}'.format(
-            train_pipeline))
-        results = dict(
-            filename='test_img.png',
-            ori_filename='test_img.png',
-            img=img,
-            img_shape=img.shape,
-            ori_shape=img.shape,
-            gt_bboxes=np.zeros((0, 4), dtype=np.float32),
-            gt_labels=np.array([], dtype=np.int64),
-            gt_masks=dummy_masks(
-                img.shape[0], img.shape[1], num_obj=0, mode=mode),
-        )
-        results['img_fields'] = ['img']
-        results['bbox_fields'] = ['gt_bboxes']
-        results['mask_fields'] = ['gt_masks']
-        output_results = train_pipeline(results)
-        assert output_results is not None
-
-        print('Test empty GT with testing data pipeline: \n{!r}'.format(
-            test_pipeline))
-        results = dict(
-            filename='test_img.png',
-            ori_filename='test_img.png',
-            img=img,
-            img_shape=img.shape,
-            ori_shape=img.shape,
-            gt_bboxes=np.zeros((0, 4), dtype=np.float32),
-            gt_labels=np.array([], dtype=np.int64),
-            gt_masks=dummy_masks(
-                img.shape[0], img.shape[1], num_obj=0, mode=mode),
-        )
-        results['img_fields'] = ['img']
-        results['bbox_fields'] = ['gt_bboxes']
-        results['mask_fields'] = ['gt_masks']
-        output_results = test_pipeline(results)
-        assert output_results is not None
-
-
 def _check_roi_head(config, head):
     # check consistency between head_config and roi_head
     assert config['type'] == head.__class__.__name__

tests/test_dataset/test_indoor_eval.py

 import numpy as np
+import pytest
 import torch
 
 from mmdet3d.core.evaluation.indoor_eval import average_precision, indoor_eval
 
 
 def test_indoor_eval():
+    if not torch.cuda.is_available():
+        pytest.skip()
     from mmdet3d.core.bbox.structures import Box3DMode, DepthInstance3DBoxes
     det_infos = [{
         'labels_3d':

tests/test_dataset/test_scannet_dataset.py

 import numpy as np
+import pytest
 import torch
 
 from mmdet3d.datasets import ScanNetDataset
@@ -111,6 +112,8 @@ def test_getitem():
 
 
 def test_evaluate():
+    if not torch.cuda.is_available():
+        pytest.skip()
     from mmdet3d.core.bbox.structures import DepthInstance3DBoxes
     root_path = './tests/data/scannet'
     ann_file = './tests/data/scannet/scannet_infos.pkl'

tests/test_dataset/test_sunrgbd_dataset.py

 import numpy as np
+import pytest
 import torch
 
 from mmdet3d.datasets import SUNRGBDDataset
@@ -95,6 +96,8 @@ def test_getitem():
 
 
 def test_evaluate():
+    if not torch.cuda.is_available():
+        pytest.skip()
     from mmdet3d.core.bbox.structures import DepthInstance3DBoxes
     root_path = './tests/data/sunrgbd'
     ann_file = './tests/data/sunrgbd/sunrgbd_infos.pkl'

tests/test_forward.py

@@ -48,10 +48,6 @@ def _get_detector_cfg(fname):
     return model, train_cfg, test_cfg
 
 
-def test_faster_rcnn_forward():
-    _test_two_stage_forward('mvxnet/faster_rcnn_r50_fpn_caffe_2x8_1x_nus.py')
-
-
 def _test_two_stage_forward(cfg_file):
     model, train_cfg, test_cfg = _get_detector_cfg(cfg_file)
     model['pretrained'] = None

tests/test_pipeline/test_transforms_3d.py

@@ -34,66 +34,6 @@ def test_remove_points_in_boxes():
     assert points.shape == (10, 4)
 
 
-def test_object_sample():
-    db_sampler = mmcv.ConfigDict({
-        'data_root': './tests/data/kitti/',
-        'info_path': './tests/data/kitti/kitti_dbinfos_train.pkl',
-        'rate': 1.0,
-        'prepare': {
-            'filter_by_difficulty': [-1],
-            'filter_by_min_points': {
-                'Pedestrian': 10
-            }
-        },
-        'classes': ['Pedestrian', 'Cyclist', 'Car'],
-        'sample_groups': {
-            'Pedestrian': 6
-        }
-    })
-    object_sample = ObjectSample(db_sampler)
-    points = np.fromfile(
-        './tests/data/kitti/training/velodyne_reduced/000000.bin',
-        np.float32).reshape(-1, 4)
-    annos = mmcv.load('./tests/data/kitti/kitti_infos_train.pkl')
-    info = annos[0]
-    rect = info['calib']['R0_rect'].astype(np.float32)
-    Trv2c = info['calib']['Tr_velo_to_cam'].astype(np.float32)
-    annos = info['annos']
-    loc = annos['location']
-    dims = annos['dimensions']
-    rots = annos['rotation_y']
-    gt_names = annos['name']
-
-    gt_bboxes_3d = np.concatenate([loc, dims, rots[..., np.newaxis]],
-                                  axis=1).astype(np.float32)
-    gt_bboxes_3d = CameraInstance3DBoxes(gt_bboxes_3d).convert_to(
-        Box3DMode.LIDAR, np.linalg.inv(rect @ Trv2c))
-    CLASSES = ('car', 'pedestrian', 'cyclist')
-    gt_labels = []
-    for cat in gt_names:
-        if cat in CLASSES:
-            gt_labels.append(CLASSES.index(cat))
-        else:
-            gt_labels.append(-1)
-    input_dict = dict(
-        points=points, gt_bboxes_3d=gt_bboxes_3d, gt_labels_3d=gt_labels)
-    input_dict = object_sample(input_dict)
-    points = input_dict['points']
-    gt_bboxes_3d = input_dict['gt_bboxes_3d']
-    gt_labels_3d = input_dict['gt_labels_3d']
-
-    expected_gt_bboxes_3d = torch.tensor(
-        [[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100],
-         [8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]])
-    expected_gt_labels_3d = np.array([-1, 0])
-    repr_str = repr(object_sample)
-    expected_repr_str = 'ObjectSample'
-    assert repr_str == expected_repr_str
-    assert points.shape == (1177, 4)
-    assert torch.allclose(gt_bboxes_3d.tensor, expected_gt_bboxes_3d)
-    assert np.all(gt_labels_3d == expected_gt_labels_3d)
-
-
 def test_object_noise():
     np.random.seed(0)
     object_noise = ObjectNoise()

tests/test_pointnet_ops.py

@@ -248,6 +248,8 @@ def test_three_interpolate():
 
 
 def test_three_nn():
+    if not torch.cuda.is_available():
+        pytest.skip()
     known = torch.tensor([[[-1.8373, 3.5605,
                             -0.7867], [0.7615, 2.9420, 0.2314],
                            [-0.6503, 3.6637, -1.0622],

tests/test_samplers.py

+import pytest
 import torch
 
 from mmdet3d.core.bbox.assigners import MaxIoUAssigner
@@ -5,6 +6,8 @@ from mmdet3d.core.bbox.samplers import IoUNegPiecewiseSampler
 
 
 def test_iou_piecewise_sampler():
+    if not torch.cuda.is_available():
+        pytest.skip()
     assigner = MaxIoUAssigner(
         pos_iou_thr=0.55,
         neg_iou_thr=0.55,