[Feature]: Support nuimages dataset and provide baseline models (#91)

* [Feature]: support using nuimages for instance segmentation

* Update performance and start benchmark

* Change default path names

* Update performance

* Update mmcv version

* Update model links

* Update model links and fix unit tests

* rephrase

.github/workflows/build.yml

@@ -38,12 +38,8 @@ jobs:
     strategy:
       matrix:
         python-version: [3.6, 3.7]
-        torch: [1.3.0, 1.5.0+cu101, 1.6.0+cu101]
+        torch: [1.5.0+cu101, 1.6.0+cu101]
         include:
-          - torch: 1.3.0
-            torchvision: 0.4.2
-            mmcv: 1.3.0+cu101
-            cuda_arch: "6.0"
           - torch: 1.5.0+cu101
             torchvision: 0.6.0+cu101
             mmcv: 1.5.0+cu101

README.md

@@ -30,6 +30,7 @@ a part of the OpenMMLab project developed by [MMLab](http://mmlab.ie.cuhk.edu.hk
 - **Support indoor/outdoor 3D detection out of box**
 
   It directly supports popular indoor and outdoor 3D detection datasets, including ScanNet, SUNRGB-D, nuScenes, Lyft, and KITTI.
+  For nuScenes dataset, we also support nuImages dataset.
 
 - **Natural integration with 2D detection**
 

configs/_base_/datasets/coco_instance.py

+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', img_scale=(1333, 800), 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', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        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,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/nuim_instance.py

+dataset_type = 'CocoDataset'
+data_root = 'data/nuimages/'
+class_names = [
+    'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
+    'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
+]
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='Resize',
+        img_scale=[(1280, 720), (1920, 1080)],
+        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', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1600, 900),
+        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,
+        ann_file=data_root + 'annotations/nuimages_v1.0-train.json',
+        img_prefix=data_root,
+        classes=class_names,
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/nuimages_v1.0-val.json',
+        img_prefix=data_root,
+        classes=class_names,
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/nuimages_v1.0-val.json',
+        img_prefix=data_root,
+        classes=class_names,
+        pipeline=test_pipeline))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/models/cascade_mask_rcnn_r50_fpn.py

+# model settings
+model = dict(
+    type='CascadeRCNN',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch'),
+    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='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        type='CascadeRoIHead',
+        num_stages=3,
+        stage_loss_weights=[1, 0.5, 0.25],
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=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=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            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=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            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=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ],
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=4,
+            in_channels=256,
+            conv_out_channels=256,
+            num_classes=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, 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,
+            match_low_quality=True,
+            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,
+        nms_post=2000,
+        max_num=2000,
+        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,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False),
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.6,
+                neg_iou_thr=0.6,
+                min_pos_iou=0.6,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False),
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.7,
+                min_pos_iou=0.7,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            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_threshold=0.5),
+        max_per_img=100,
+        mask_thr_binary=0.5))

configs/_base_/models/mask_rcnn_r50_fpn.py

+# model settings
+model = dict(
+    type='MaskRCNN',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch'),
+    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', output_size=7, sampling_ratio=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)),
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=4,
+            in_channels=256,
+            conv_out_channels=256,
+            num_classes=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, 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,
+            match_low_quality=True,
+            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,
+        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,
+            match_low_quality=True,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=512,
+            pos_fraction=0.25,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=True),
+        mask_size=28,
+        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_threshold=0.5),
+        max_per_img=100,
+        mask_thr_binary=0.5))

configs/_base_/schedules/mmdet_schedule_1x.py

+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[8, 11])
+total_epochs = 12

configs/nuimages/README.md

+# PointPillars: Fast Encoders for Object Detection from Point Clouds
+
+## Introduction
+
+We support and provide some baseline results on [nuImages dataset](https://www.nuscenes.org/nuimages).
+We follow the class mapping in nuScenes dataset, which maps the original categories into 10 foreground categories.
+The baseline results includes instance segmentation models, e.g., Mask R-CNN and Cascade Mask R-CNN.
+We will support panoptic segmentation models in the future.
+
+
+## Results
+
+### Instance Segmentation
+
+We report Mask R-CNN and Cascade Mask R-CNN results on nuimages.
+
+|Method |  |Backbone| Lr schd | Mem (GB) | Box AP  | Mask AP  |Download |
+| :---------: |:---------: | :---------: | :-----: |:-----: | :------: | :------------: | :----: | :------: |
+| Mask R-CNN| [R-50](./mask_rcnn_r50_fpn_1x_nuim.py) |IN|1x|7.4|47.8 |38.4|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r50_fpn_1x_nuim/mask_rcnn_r50_fpn_1x_nuim_20200906_114546-902bb808.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r50_fpn_1x_nuim/mask_rcnn_r50_fpn_1x_nuim_20200906_114546.log.json)|
+| Mask R-CNN| [R-50](./mask_rcnn_r50_fpn_coco-2x_1x_nuim.py) |IN+COCO-2x|1x|7.4|49.6|40.0|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r50_fpn_coco-2x_1x_nuim/mask_rcnn_r50_fpn_coco-2x_1x_nuim_20200905_234546-01b6b9ba.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r50_fpn_coco-2x_1x_nuim/mask_rcnn_r50_fpn_coco-2x_1x_nuim_20200905_234546.log.json)|
+| Mask R-CNN| [R-50-CAFFE](./mask_rcnn_r50_caffe_fpn_1x_nuim.py) |IN|1x|7.0|47.7|38.2|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r50_caffe_fpn_1x_nuim/mask_rcnn_r50_caffe_fpn_1x_nuim_20200906_120052-733905fa.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r50_caffe_fpn_1x_nuim/mask_rcnn_r50_caffe_fpn_1x_nuim_20200906_120052.log.json)|
+| Mask R-CNN| [R-50-CAFFE](./mask_rcnn_r50_caffe_fpn_coco-3x_1x_nuim.py) |IN+COCO-3x|1x|7.0|49.7|40.3|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r50_caffe_fpn_coco-3x_1x_nuim/mask_rcnn_r50_caffe_fpn_coco-3x_1x_nuim_20200906_134613-e6dc1931.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r50_caffe_fpn_coco-3x_1x_nuim/mask_rcnn_r50_caffe_fpn_coco-3x_1x_nuim_20200906_134613.log.json)|
+| Mask R-CNN| [R-101](./mask_rcnn_r101_fpn_1x_nuim.py) |IN|1x|10.9|48.9|38.9|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r101_fpn_1x_nuim/mask_rcnn_r101_fpn_1x_nuim_20200906_182752-823be521.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_r101_fpn_1x_nuim/mask_rcnn_r101_fpn_1x_nuim_20200906_182752.log.json)|
+| Mask R-CNN| [X-101_32x4d](./mask_rcnn_x101_32x4d_fpn_1x_nuim.py) |IN|1x|13.3|50.3|40.1|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_x101_32x4d_fpn_1x_nuim/mask_rcnn_x101_32x4d_fpn_1x_nuim_20200906_134611-bd241530.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/mask_rcnn_x101_32x4d_fpn_1x_nuim/mask_rcnn_x101_32x4d_fpn_1x_nuim_20200906_134611.log.json)|
+| Cascade Mask R-CNN| [R-50](./cascade_mask_rcnn_r50_fpn_1x_nuim.py) |IN|1x|8.9|50.8|40.1|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/cascade_mask_rcnn_r50_fpn_1x_nuim/cascade_mask_rcnn_r50_fpn_1x_nuim_20200906_114546-22bf3085.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/cascade_mask_rcnn_r50_fpn_1x_nuim/cascade_mask_rcnn_r50_fpn_1x_nuim_20200906_114546.log.json)|
+| Cascade Mask R-CNN| [R-101](./cascade_mask_rcnn_r101_fpn_1x_nuim.py) |IN|1x|12.5|51.8|40.6|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/cascade_mask_rcnn_r101_fpn_1x_nuim/cascade_mask_rcnn_r101_fpn_1x_nuim_20200906_134611-ee279b07.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/cascade_mask_rcnn_r101_fpn_1x_nuim/cascade_mask_rcnn_r101_fpn_1x_nuim_20200906_134611.log.json)|
+| Cascade Mask R-CNN| [X-101_32x4d](./cascade_mask_rcnn_x101_32x4d_fpn_1x_nuim.py) |IN|1x|14.9|52.9|41.6|[model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/cascade_mask_rcnn_x101_32x4d_fpn_1x_nuim/cascade_mask_rcnn_x101_32x4d_fpn_1x_nuim_20200906_134611-47db31b0.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection3d/v0.1.0_models/nuimages/cascade_mask_rcnn_x101_32x4d_fpn_1x_nuim/cascade_mask_rcnn_x101_32x4d_fpn_1x_nuim_20200906_134611.log.json)|
+
+**Note**:
+1. `IN` means only using ImageNet pre-trained backbone. `IN+COCO-Nx` means the backbone is first pre-trained on ImageNet, and then the detector is pre-trained on COCO train2017 dataset by `Nx` schedules.
+2. All the training hyper-parameters follows the standard 1x schedules on COCO dataset except that the images are resized from
+1280 x 720 to 1920 x 1080 (relative ratio 0.8 to 1.2) since the images are in size 1600 x 900.

configs/nuimages/cascade_mask_rcnn_r101_fpn_1x_nuim.py

+_base_ = './cascade_mask_rcnn_r50_fpn_1x_nuim.py'
+model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))

configs/nuimages/cascade_mask_rcnn_r50_fpn_1x_nuim.py

+_base_ = [
+    '../_base_/models/cascade_mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/nuim_instance.py',
+    '../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
+]
+model = dict(
+    roi_head=dict(
+        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=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            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=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            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=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ],
+        mask_head=dict(num_classes=10)))

configs/nuimages/cascade_mask_rcnn_x101_32x4d_fpn_1x_nuim.py

+_base_ = './cascade_mask_rcnn_r50_fpn_1x_nuim.py'
+model = dict(
+    pretrained='open-mmlab://resnext101_32x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        style='pytorch'))

configs/nuimages/mask_rcnn_r101_fpn_1x_nuim.py

+_base_ = './mask_rcnn_r50_fpn_1x_nuim.py'
+model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))

configs/nuimages/mask_rcnn_r50_caffe_fpn_1x_nuim.py

+_base_ = [
+    '../_base_/models/mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/nuim_instance.py',
+    '../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
+]
+model = dict(
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(norm_cfg=dict(requires_grad=False), style='caffe'),
+    roi_head=dict(
+        bbox_head=dict(num_classes=10), mask_head=dict(num_classes=10)))
+# use caffe img_norm
+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=True),
+    dict(
+        type='Resize',
+        img_scale=[(1280, 720), (1920, 1080)],
+        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', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1600, 900),
+        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(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))

configs/nuimages/mask_rcnn_r50_caffe_fpn_coco-3x_1x_nuim.py

+_base_ = [
+    '../_base_/models/mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/nuim_instance.py',
+    '../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
+]
+model = dict(
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(norm_cfg=dict(requires_grad=False), style='caffe'),
+    roi_head=dict(
+        bbox_head=dict(num_classes=10), mask_head=dict(num_classes=10)))
+# use caffe img_norm
+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=True),
+    dict(
+        type='Resize',
+        img_scale=[(1280, 720), (1920, 1080)],
+        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', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1600, 900),
+        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(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))
+
+load_from = 'http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth'  # noqa

configs/nuimages/mask_rcnn_r50_fpn_1x_nuim.py

+_base_ = [
+    '../_base_/models/mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/nuim_instance.py',
+    '../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
+]
+model = dict(
+    roi_head=dict(
+        bbox_head=dict(num_classes=10), mask_head=dict(num_classes=10)))

configs/nuimages/mask_rcnn_r50_fpn_coco-2x_1x_nuim.py

+_base_ = [
+    '../_base_/models/mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/nuim_instance.py',
+    '../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
+]
+model = dict(
+    roi_head=dict(
+        bbox_head=dict(num_classes=10), mask_head=dict(num_classes=10)))
+load_from = 'http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_2x_coco/mask_rcnn_r50_fpn_2x_coco_bbox_mAP-0.392__segm_mAP-0.354_20200505_003907-3e542a40.pth'  # noqa

configs/nuimages/mask_rcnn_x101_32x4d_fpn_1x_nuim.py

+_base_ = './mask_rcnn_r50_fpn_1x_nuim.py'
+model = dict(
+    pretrained='open-mmlab://resnext101_32x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        style='pytorch'))

requirements/runtime.txt

@@ -2,7 +2,7 @@ lyft_dataset_sdk
 networkx>=2.2,<2.3
 # we may unlock the verion of numba in the future
 numba==0.48.0
-nuscenes-devkit==1.0.5
+nuscenes-devkit
 plyfile
 # by default we also use tensorboard to log results
 tensorboard

setup.cfg

@@ -8,6 +8,6 @@ line_length = 79
 multi_line_output = 0
 known_standard_library = setuptools
 known_first_party = mmdet,mmdet3d
-known_third_party = cv2,load_scannet_data,lyft_dataset_sdk,m2r,matplotlib,mmcv,numba,numpy,nuscenes,pandas,plyfile,pycocotools,pyquaternion,pytest,recommonmark,scannet_utils,scipy,seaborn,shapely,skimage,sunrgbd_utils,terminaltables,torch,torchvision,trimesh
+known_third_party = cv2,load_scannet_data,lyft_dataset_sdk,m2r,matplotlib,mmcv,nuimages,numba,numpy,nuscenes,pandas,plyfile,pycocotools,pyquaternion,pytest,recommonmark,scannet_utils,scipy,seaborn,shapely,skimage,sunrgbd_utils,terminaltables,torch,torchvision,trimesh
 no_lines_before = STDLIB,LOCALFOLDER
 default_section = THIRDPARTY

tests/test_config.py

@@ -139,8 +139,8 @@ def _check_roi_extractor(config, roi_extractor, prev_roi_extractor=None):
     assert (len(config.featmap_strides) == len(roi_extractor.roi_layers))
     assert (config.out_channels == roi_extractor.out_channels)
     from torch.nn.modules.utils import _pair
-    assert (_pair(
-        config.roi_layer.out_size) == roi_extractor.roi_layers[0].out_size)
+    assert (_pair(config.roi_layer.output_size) ==
+            roi_extractor.roi_layers[0].output_size)
 
     if 'use_torchvision' in config.roi_layer:
         assert (config.roi_layer.use_torchvision ==