Merge branch 'add-github-action' into 'master'

Add Github Action

See merge request open-mmlab/mmdet.3d!149

.github/workflows/build.yml

+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: build
+
+on: [push, pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.7
+        uses: actions/setup-python@v1
+        with:
+          python-version: 3.7
+      - name: Install linting dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 isort yapf interrogate
+      - name: Lint with flake8
+        run: flake8 .
+      - name: Lint with isort
+        run: isort --recursive --check-only --diff mmdet3d/ tests/ examples/
+      - 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
+
+  build:
+    env:
+      CUDA: 10.1.105-1
+      CUDA_SHORT: 10.1
+      UBUNTU_VERSION: ubuntu1804
+      FORCE_CUDA: 1
+      MMCV_CUDA_ARGS: -gencode=arch=compute_61,code=sm_61
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.6, 3.7]
+        torch: [1.3.0+cpu, 1.5.0+cpu]
+        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
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        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}
+          sudo dpkg -i ${INSTALLER}
+          wget https://developer.download.nvidia.com/compute/cuda/repos/${UBUNTU_VERSION}/x86_64/7fa2af80.pub
+          sudo apt-key add 7fa2af80.pub
+          sudo apt update -qq
+          sudo apt install -y cuda-${CUDA_SHORT/./-} cuda-cufft-dev-${CUDA_SHORT/./-}
+          sudo apt clean
+          export CUDA_HOME=/usr/local/cuda-${CUDA_SHORT}
+          export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:${CUDA_HOME}/include:${LD_LIBRARY_PATH}
+          export PATH=${CUDA_HOME}/bin:${PATH}
+          sudo apt-get install -y ninja-build
+      - name: Install Pillow
+        if: ${{matrix.torchvision == '0.4.2+cpu'}}
+        run: pip install Pillow==6.2.2
+      - name: Install PyTorch
+        run: pip install torch==${{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 -r requirements.txt
+      - name: Build and install
+        run: rm -rf .eggs && pip install -e .
+      - name: Run unittests and generate coverage report
+        run: |
+          coverage run --branch --source mmdet3d -m pytest tests/
+          coverage xml
+          coverage report -m --omit="mmdet3d/utils/*","mmdet3d/apis/*"
+      # Only upload coverage report for python3.7 && pytorch1.5
+      - name: Upload coverage to Codecov
+        if: ${{matrix.torch == '1.5.0+cu101' && matrix.python-version == '3.7'}}
+        uses: codecov/codecov-action@v1.0.10
+        with:
+          file: ./coverage.xml
+          flags: unittests
+          env_vars: OS,PYTHON
+          name: codecov-umbrella
+          fail_ci_if_error: false

README.md

@@ -13,7 +13,7 @@ The master branch works with **PyTorch 1.3 to 1.5**.
 MMDetection3D is an open source object detection toolbox based on PyTorch, towards the next-generation platform for general 3D detection. It is
 a part of the OpenMMLab project developed by [MMLab](http://mmlab.ie.cuhk.edu.hk/).
 
-![demo image](resources/outdoor_demo.gif)
+![demo image](resources/mmdet3d_outdoor_demo.gif)
 
 ### Major features
 

configs/mvxnet/faster_rcnn_r50_fpn_caffe_1x_kitti-2d-3class_coco-3x-pretrain.py

-# model settings
-norm_cfg = dict(type='BN', requires_grad=False)
-model = dict(
-    type='FasterRCNN',
-    pretrained=('open-mmlab://detectron2/resnet50_caffe'),
-    backbone=dict(
-        type='ResNet',
-        depth=50,
-        num_stages=4,
-        out_indices=(0, 1, 2, 3),
-        frozen_stages=1,
-        norm_cfg=norm_cfg,
-        norm_eval=True,
-        style='caffe'),
-    neck=dict(
-        type='FPN',
-        in_channels=[256, 512, 1024, 2048],
-        out_channels=256,
-        num_outs=5),
-    rpn_head=dict(
-        type='RPNHead',
-        in_channels=256,
-        feat_channels=256,
-        anchor_generator=dict(
-            type='AnchorGenerator',
-            scales=[8],
-            ratios=[0.5, 1.0, 2.0],
-            strides=[4, 8, 16, 32, 64]),
-        bbox_coder=dict(
-            type='DeltaXYWHBBoxCoder',
-            target_means=[.0, .0, .0, .0],
-            target_stds=[1.0, 1.0, 1.0, 1.0]),
-        loss_cls=dict(
-            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
-        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
-    roi_head=dict(
-        type='StandardRoIHead',
-        bbox_roi_extractor=dict(
-            type='SingleRoIExtractor',
-            roi_layer=dict(type='RoIAlign', out_size=7, sample_num=0),
-            out_channels=256,
-            featmap_strides=[4, 8, 16, 32]),
-        bbox_head=dict(
-            type='Shared2FCBBoxHead',
-            in_channels=256,
-            fc_out_channels=1024,
-            roi_feat_size=7,
-            num_classes=80,
-            bbox_coder=dict(
-                type='DeltaXYWHBBoxCoder',
-                target_means=[0., 0., 0., 0.],
-                target_stds=[0.1, 0.1, 0.2, 0.2]),
-            reg_class_agnostic=False,
-            loss_cls=dict(
-                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
-            loss_bbox=dict(type='L1Loss', loss_weight=1.0))))
-# model training and testing settings
-train_cfg = dict(
-    rpn=dict(
-        assigner=dict(
-            type='MaxIoUAssigner',
-            pos_iou_thr=0.7,
-            neg_iou_thr=0.3,
-            min_pos_iou=0.3,
-            ignore_iof_thr=-1),
-        sampler=dict(
-            type='RandomSampler',
-            num=256,
-            pos_fraction=0.5,
-            neg_pos_ub=-1,
-            add_gt_as_proposals=False),
-        allowed_border=0,
-        pos_weight=-1,
-        debug=False),
-    rpn_proposal=dict(
-        nms_across_levels=False,
-        nms_pre=2000,
-        # following the setting of detectron,
-        # which improves ~0.2 bbox mAP.
-        nms_post=1000,
-        max_num=1000,
-        nms_thr=0.7,
-        min_bbox_size=0),
-    rcnn=dict(
-        assigner=dict(
-            type='MaxIoUAssigner',
-            pos_iou_thr=0.5,
-            neg_iou_thr=0.5,
-            min_pos_iou=0.5,
-            ignore_iof_thr=-1),
-        sampler=dict(
-            type='RandomSampler',
-            num=512,
-            pos_fraction=0.25,
-            neg_pos_ub=-1,
-            add_gt_as_proposals=True),
-        pos_weight=-1,
-        debug=False))
-test_cfg = dict(
-    rpn=dict(
-        nms_across_levels=False,
-        nms_pre=1000,
-        nms_post=1000,
-        max_num=1000,
-        nms_thr=0.7,
-        min_bbox_size=0),
-    rcnn=dict(
-        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100)
-    # soft-nms is also supported for rcnn testing
-    # e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
-)
-# dataset settings
-dataset_type = 'Kitti2DDataset'
-data_root = 'data/kitti/'
-class_names = ['Car', 'Pedestrian', 'Cyclist']
-# Values to be used for image normalization (BGR order)
-# Default mean pixel value from ImageNet: [103.53, 116.28, 123.675]
-# When using pre-trained models in Detectron1 or any MSRA models,
-# std has been absorbed into its conv1 weights, so the std needs to be set 1.
-img_norm_cfg = dict(
-    mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations', with_bbox=True, with_mask=False),
-    dict(
-        type='Resize',
-        img_scale=[(640, 192), (2560, 768)],
-        multiscale_mode='range',
-        keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1280, 384),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        class_names=class_names,
-        ann_file='kitti_infos_train.pkl',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        class_names=class_names,
-        ann_file='kitti_infos_val.pkl',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        class_names=class_names,
-        ann_file='kitti_infos_val.pkl',
-        pipeline=test_pipeline))
-# optimizer
-optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
-# learning policy
-lr_config = dict(
-    policy='step',
-    warmup='linear',
-    warmup_iters=1000,
-    warmup_ratio=1.0 / 1000,
-    step=[8, 11])
-checkpoint_config = dict(interval=1)
-# yapf:disable
-log_config = dict(
-    interval=50,
-    hooks=[
-        dict(type='TextLoggerHook'),
-        dict(type='TensorboardLoggerHook')
-    ])
-# yapf:enable
-evaluation = dict(interval=1)
-# runtime settings
-total_epochs = 12
-dist_params = dict(backend='nccl', port=29501)
-log_level = 'INFO'
-work_dir = './work_dirs/faster_rcnn_r50_fpn_1x'
-load_from = './pretrain_mmdet/faster_r50_fpn_detectron2-caffe_freezeBN_l1-loss_roialign-v2_3x-4767dd8e.pth'  # noqa
-resume_from = None
-workflow = [('train', 1)]

configs/mvxnet/faster_rcnn_r50_fpn_caffe_2x8_1x_nus.py

-# model settings
-norm_cfg = dict(type='BN', requires_grad=False)
-model = dict(
-    type='FasterRCNN',
-    pretrained=('open-mmlab://detectron2/resnet50_caffe'),
-    backbone=dict(
-        type='ResNet',
-        depth=50,
-        num_stages=4,
-        out_indices=(0, 1, 2, 3),
-        frozen_stages=1,
-        norm_cfg=norm_cfg,
-        norm_eval=True,
-        style='caffe'),
-    neck=dict(
-        type='FPN',
-        in_channels=[256, 512, 1024, 2048],
-        out_channels=256,
-        num_outs=5),
-    rpn_head=dict(
-        type='RPNHead',
-        in_channels=256,
-        feat_channels=256,
-        anchor_generator=dict(
-            type='AnchorGenerator',
-            scales=[8],
-            ratios=[0.5, 1.0, 2.0],
-            strides=[4, 8, 16, 32, 64]),
-        bbox_coder=dict(
-            type='DeltaXYWHBBoxCoder',
-            target_means=[.0, .0, .0, .0],
-            target_stds=[1.0, 1.0, 1.0, 1.0]),
-        loss_cls=dict(
-            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
-        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
-    roi_head=dict(
-        type='StandardRoIHead',
-        bbox_roi_extractor=dict(
-            type='SingleRoIExtractor',
-            roi_layer=dict(type='RoIAlign', out_size=7, sample_num=0),
-            out_channels=256,
-            featmap_strides=[4, 8, 16, 32]),
-        bbox_head=dict(
-            type='Shared2FCBBoxHead',
-            in_channels=256,
-            fc_out_channels=1024,
-            roi_feat_size=7,
-            num_classes=10,
-            bbox_coder=dict(
-                type='DeltaXYWHBBoxCoder',
-                target_means=[0., 0., 0., 0.],
-                target_stds=[0.1, 0.1, 0.2, 0.2]),
-            reg_class_agnostic=False,
-            loss_cls=dict(
-                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
-            loss_bbox=dict(type='L1Loss', loss_weight=1.0))))
-# model training and testing settings
-train_cfg = dict(
-    rpn=dict(
-        assigner=dict(
-            type='MaxIoUAssigner',
-            pos_iou_thr=0.7,
-            neg_iou_thr=0.3,
-            min_pos_iou=0.3,
-            ignore_iof_thr=-1),
-        sampler=dict(
-            type='RandomSampler',
-            num=256,
-            pos_fraction=0.5,
-            neg_pos_ub=-1,
-            add_gt_as_proposals=False),
-        allowed_border=-1,
-        pos_weight=-1,
-        debug=False),
-    rpn_proposal=dict(
-        nms_across_levels=False,
-        nms_pre=2000,
-        # following the setting of detectron,
-        # which improves ~0.2 bbox mAP.
-        nms_post=1000,
-        max_num=1000,
-        nms_thr=0.7,
-        min_bbox_size=0),
-    rcnn=dict(
-        assigner=dict(
-            type='MaxIoUAssigner',
-            pos_iou_thr=0.5,
-            neg_iou_thr=0.5,
-            min_pos_iou=0.5,
-            ignore_iof_thr=-1),
-        sampler=dict(
-            type='RandomSampler',
-            num=512,
-            pos_fraction=0.25,
-            neg_pos_ub=-1,
-            add_gt_as_proposals=True),
-        pos_weight=-1,
-        debug=False))
-test_cfg = dict(
-    rpn=dict(
-        nms_across_levels=False,
-        nms_pre=1000,
-        nms_post=1000,
-        max_num=1000,
-        nms_thr=0.7,
-        min_bbox_size=0),
-    rcnn=dict(
-        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100)
-    # soft-nms is also supported for rcnn testing
-    # e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
-)
-# dataset settings
-dataset_type = 'CocoDataset'
-data_root = 'data/nuscenes/'
-# Values to be used for image normalization (BGR order)
-# Default mean pixel values are from ImageNet: [103.53, 116.28, 123.675]
-# When using pre-trained models in Detectron1 or any MSRA models,
-# std has been absorbed into its conv1 weights, so the std needs to be set 1.
-classes = ('car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
-           'motorcycle', 'pedestrian', 'traffic_cone', 'barrier')
-img_norm_cfg = dict(
-    mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
-
-# file_client_args = dict(backend='disk')
-file_client_args = dict(
-    backend='petrel',
-    path_mapping=dict({
-        './data/nuscenes/': 's3://nuscenes/nuscenes/',
-        'data/nuscenes/': 's3://nuscenes/nuscenes/'
-    }))
-train_pipeline = [
-    dict(type='LoadImageFromFile', file_client_args=file_client_args),
-    dict(
-        type='LoadAnnotations',
-        with_bbox=True,
-        with_mask=False,
-        file_client_args=file_client_args),
-    dict(
-        type='Resize',
-        img_scale=(1280, 720),
-        ratio_range=(0.75, 1.25),
-        keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile', file_client_args=file_client_args),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1280, 720),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type=dataset_type,
-        classes=classes,
-        ann_file=data_root + 'nuscenes_infos_train.coco.json',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        classes=classes,
-        ann_file=data_root + 'nuscenes_infos_val.coco.json',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        classes=classes,
-        ann_file=data_root + 'nuscenes_infos_val.coco.json',
-        pipeline=test_pipeline))
-# optimizer
-optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
-# learning policy
-lr_config = dict(
-    policy='step',
-    warmup='linear',
-    warmup_iters=1000,
-    warmup_ratio=1.0 / 1000,
-    step=[8, 11])
-checkpoint_config = dict(interval=1)
-# yapf:disable
-log_config = dict(
-    interval=50,
-    hooks=[
-        dict(type='TextLoggerHook'),
-        dict(type='TensorboardLoggerHook')
-    ])
-# yapf:enable
-evaluation = dict(interval=1)
-# runtime settings
-total_epochs = 12
-dist_params = dict(backend='nccl', port=29501)
-log_level = 'INFO'
-work_dir = './work_dirs/faster_rcnn_r50_fpn_1x'
-load_from = './pretrain_mmdet/faster_r50_fpn_detectron2-caffe_freezeBN_l1-loss_roialign-v2_3x-4767dd8e.pth'  # noqa
-resume_from = None
-workflow = [('train', 1)]

mmdet3d/datasets/__init__.py

 from mmdet.datasets.builder import DATASETS, build_dataloader, build_dataset
 from .custom_3d import Custom3DDataset
-from .kitti2d_dataset import Kitti2DDataset
 from .kitti_dataset import KittiDataset
 from .lyft_dataset import LyftDataset
 from .nuscenes_dataset import NuScenesDataset
@@ -15,9 +14,9 @@ from .sunrgbd_dataset import SUNRGBDDataset
 __all__ = [
     'KittiDataset', 'GroupSampler', 'DistributedGroupSampler',
     'build_dataloader', 'RepeatFactorDataset', 'DATASETS', 'build_dataset',
-    'CocoDataset', 'Kitti2DDataset', 'NuScenesDataset', 'LyftDataset',
-    'ObjectSample', 'RandomFlip3D', 'ObjectNoise', 'GlobalRotScaleTrans',
-    'PointShuffle', 'ObjectRangeFilter', 'PointsRangeFilter', 'Collect3D',
+    'CocoDataset', 'NuScenesDataset', 'LyftDataset', 'ObjectSample',
+    'RandomFlip3D', 'ObjectNoise', 'GlobalRotScaleTrans', 'PointShuffle',
+    'ObjectRangeFilter', 'PointsRangeFilter', 'Collect3D',
     'LoadPointsFromFile', 'NormalizePointsColor', 'IndoorPointSample',
     'LoadAnnotations3D', 'SUNRGBDDataset', 'ScanNetDataset', 'Custom3DDataset',
     'LoadPointsFromMultiSweeps'