add RepPoints support (#1256)

* add reppoints head, reppoints detector and the config files.

* add reppoints generator, target and the center-based assigner.

* add readme for RepPoints

configs/reppoints/README.md

+# RepPoints: Point Set Representation for Object Detection
+
+By [Ze Yang](https://yangze.tech/), [Shaohui Liu](http://b1ueber2y.me/), and [Han Hu](https://ancientmooner.github.io/).
+
+We provide code support and configuration files to reproduce the results in the paper for
+["RepPoints: Point Set Representation for Object Detection"](https://arxiv.org/abs/1904.11490) on COCO object detection. 
+
+## Introduction
+
+**RepPoints**, initially described in [arXiv](https://arxiv.org/abs/1904.11490), is a new representation method for visual objects, on which visual understanding tasks are typically centered. Visual object representation, aiming at both geometric description and appearance feature extraction, is conventionally achieved by `bounding box + RoIPool (RoIAlign)`. The bounding box representation is convenient to use; however, it provides only a rectangular localization of objects that lacks geometric precision and may consequently degrade feature quality. Our new representation, RepPoints, models objects by a `point set` instead of a `bounding box`, which learns to adaptively position themselves over an object in a manner that circumscribes the object’s `spatial extent` and enables `semantically aligned feature extraction`. This richer and more flexible representation maintains the convenience of bounding boxes while facilitating various visual understanding applications. This repo demonstrated the effectiveness of RepPoints for COCO object detection.
+
+Another feature of this repo is the demonstration of an `anchor-free detector`, which can be as effective as state-of-the-art anchor-based detection methods. The anchor-free detector can utilize either `bounding box` or `RepPoints` as the basic object representation.
+
+<div align="center">
+  <img src="reppoints.png" width="400px" />
+  <p>Learning RepPoints in Object Detection.</p>
+</div>
+
+## Citing RepPoints
+
+```
+@inproceedings{yang2019reppoints,
+  title={RepPoints: Point Set Representation for Object Detection},
+  author={Yang, Ze and Liu, Shaohui and Hu, Han and Wang, Liwei and Lin, Stephen},
+  booktitle={The IEEE International Conference on Computer Vision (ICCV)},
+  month={Oct},
+  year={2019}
+}
+```
+
+## Results and models
+
+The results on COCO 2017val are shown in the table below.
+
+| Method | Backbone | Anchor | convert func | Lr schd | box AP | Download |
+| :----: | :------: | :-------: | :------: | :-----: | :----: | :------: |
+| BBox | R-50-FPN | single | -    | 1x      | 36.3|[model](https://drive.google.com/open?id=1TaVAFGZP2i7RwtlQjy3LBH1WI-YRH774) |
+| BBox | R-50-FPN | none     | -    | 1x      | 37.3| [model](https://drive.google.com/open?id=1hpfu-I7gtZnIb0NU2WvUvaZz_dm-THuZ) |
+| RepPoints | R-50-FPN | none     | partial MinMax | 1x      | 38.1| [model](https://drive.google.com/open?id=11zFtdKH-QGz_zH7vlcIih6FQAjV84CWc) |
+| RepPoints | R-50-FPN | none     | MinMax | 1x      | 38.2| [model](https://drive.google.com/open?id=1Cg9818dpkL-9qjmYdkhrY_BRiQFjV4xu)  |
+| RepPoints | R-50-FPN | none     | moment | 1x      | 38.2| [model](https://drive.google.com/open?id=1rQg-lE-5nuqO1bt6okeYkti4Q-EaBsu_) |
+| RepPoints | R-50-FPN | none     | moment | 2x      | 38.6| [model](https://drive.google.com/open?id=1TfR-5geVviKhRoXL9JP6cG3fkN2itbBU) |
+| RepPoints | R-50-FPN | none     | moment | 2x (ms train)   | 40.8| [model](https://drive.google.com/open?id=1oaHTIaP51oB5HJ6GWV3WYK19lMm9iJO6) |
+| RepPoints | R-50-FPN | none     | moment | 2x (ms train&ms test)   | 42.2|          |
+| RepPoints | R-101-FPN | none   | moment | 2x   | 40.3| [model](https://drive.google.com/open?id=1BAmGeUQ_zVQi2u7rgOuPQem2EjXDLgWm) |
+| RepPoints | R-101-FPN | none   | moment | 2x (ms train)   | 42.3| [model](https://drive.google.com/open?id=14Lf0p4fXElXaxFu8stk3hek3bY8tNENX) |
+| RepPoints | R-101-FPN | none   | moment | 2x (ms train&ms test)   | 44.1|          |
+| RepPoints | R-101-FPN-DCN | none   | moment | 2x   | 43.0| [model](https://drive.google.com/open?id=1hpptxpb4QtNuB-HnV5wHbDltPHhlYq4z) |
+| RepPoints | R-101-FPN-DCN | none   | moment | 2x (ms train)   | 44.8| [model](https://drive.google.com/open?id=1fsTckK99HYjOURwcFeHfy5JRRtsCajfX) |
+| RepPoints | R-101-FPN-DCN | none   | moment | 2x (ms train&ms test)   | 46.4|          |
+| RepPoints | X-101-FPN-DCN | none   | moment | 2x   | 44.5| [model](https://drive.google.com/open?id=1Y8vqaqU88-FEqqwl6Zb9exD5O246yrMR) |
+| RepPoints | X-101-FPN-DCN | none   | moment | 2x (ms train)   | 45.6| [model](https://drive.google.com/open?id=1nr9gcVWxzeakbfPC6ON9yvKOuLzj_RrJ) |
+| RepPoints | X-101-FPN-DCN | none   | moment | 2x (ms train&ms test)   | 46.8|          |
+
+**Notes:**
+
+- `R-xx`, `X-xx` denote the ResNet and ResNeXt architectures, respectively. 
+- `DCN` denotes replacing 3x3 conv with the 3x3 deformable convolution in `c3-c5` stages of backbone.
+- `none` in the `anchor` column means 2-d `center point` (x,y) is used to represent the initial object hypothesis. `single` denotes one 4-d anchor box (x,y,w,h) with IoU based label assign criterion is adopted. 
+- `moment`, `partial MinMax`, `MinMax` in the `convert func` column are three functions to convert a point set to a pseudo box.
+- `ms` denotes multi-scale training or multi-scale test.
+- Note the results here are slightly different from those reported in the paper, due to framework change. While the original paper uses an [MXNet](https://mxnet.apache.org/) implementation, we re-implement the method in [PyTorch](https://pytorch.org/) based on mmdetection.

configs/reppoints/bbox_r50_grid_center_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='minmax',
+        use_grid_points=True))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/bbox_r50_grid_center_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/bbox_r50_grid_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='minmax',
+        use_grid_points=True))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/bbox_r50_grid_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_minmax_r50_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='minmax'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_minmax_r50_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r101_dcn_fpn_2x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet101',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        dcn=dict(
+            modulated=False, deformable_groups=1, fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r101_dcn_fpn_2x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r101_dcn_fpn_2x_mt.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet101',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        dcn=dict(
+            modulated=False, deformable_groups=1, fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 960)],
+        keep_ratio=True,
+        multiscale_mode='range'),
+    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=(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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r101_dcn_fpn_2x_mt'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r101_fpn_2x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet101',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r101_fpn_2x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r101_fpn_2x_mt.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet101',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 960)],
+        keep_ratio=True,
+        multiscale_mode='range'),
+    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=(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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r101_fpn_2x_mt'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r50_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r50_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r50_fpn_2x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r50_fpn_2x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r50_fpn_2x_mt.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 960)],
+        keep_ratio=True,
+        multiscale_mode='range'),
+    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=(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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r50_fpn_2x_mt'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_x101_dcn_fpn_2x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    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,
+        style='pytorch',
+        dcn=dict(
+            modulated=False,
+            groups=32,
+            deformable_groups=1,
+            fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_x101_dcn_fpn_2x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_x101_dcn_fpn_2x_mt.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    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,
+        style='pytorch',
+        dcn=dict(
+            modulated=False,
+            groups=32,
+            deformable_groups=1,
+            fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 960)],
+        keep_ratio=True,
+        multiscale_mode='range'),
+    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=(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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_x101_dcn_fpn_2x_mt'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_partial_minmax_r50_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='partial_minmax'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    nms=dict(type='nms', iou_thr=0.5),
+    max_per_img=100)
+# dataset settings
+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),
+    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']),
+]
+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(
+    imgs_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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, 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=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_partial_minmax_r50_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

mmdet/core/anchor/__init__.py

 from .anchor_generator import AnchorGenerator
 from .anchor_target import anchor_inside_flags, anchor_target
 from .guided_anchor_target import ga_loc_target, ga_shape_target
+from .point_generator import PointGenerator
+from .point_target import point_target
 
 __all__ = [
     'AnchorGenerator', 'anchor_target', 'anchor_inside_flags', 'ga_loc_target',
-    'ga_shape_target'
+    'ga_shape_target', 'PointGenerator', 'point_target'
 ]

mmdet/core/anchor/point_generator.py

+import torch
+
+
+class PointGenerator(object):
+
+    def _meshgrid(self, x, y, row_major=True):
+        xx = x.repeat(len(y))
+        yy = y.view(-1, 1).repeat(1, len(x)).view(-1)
+        if row_major:
+            return xx, yy
+        else:
+            return yy, xx
+
+    def grid_points(self, featmap_size, stride=16, device='cuda'):
+        feat_h, feat_w = featmap_size
+        shift_x = torch.arange(0., feat_w, device=device) * stride
+        shift_y = torch.arange(0., feat_h, device=device) * stride
+        shift_xx, shift_yy = self._meshgrid(shift_x, shift_y)
+        stride = shift_x.new_full((shift_xx.shape[0], ), stride)
+        shifts = torch.stack([shift_xx, shift_yy, stride], dim=-1)
+        all_points = shifts.to(device)
+        return all_points
+
+    def valid_flags(self, featmap_size, valid_size, device='cuda'):
+        feat_h, feat_w = featmap_size
+        valid_h, valid_w = valid_size
+        assert valid_h <= feat_h and valid_w <= feat_w
+        valid_x = torch.zeros(feat_w, dtype=torch.uint8, device=device)
+        valid_y = torch.zeros(feat_h, dtype=torch.uint8, device=device)
+        valid_x[:valid_w] = 1
+        valid_y[:valid_h] = 1
+        valid_xx, valid_yy = self._meshgrid(valid_x, valid_y)
+        valid = valid_xx & valid_yy
+        return valid

mmdet/core/anchor/point_target.py

+import torch
+
+from ..bbox import PseudoSampler, assign_and_sample, build_assigner
+from ..utils import multi_apply
+
+
+def point_target(proposals_list,
+                 valid_flag_list,
+                 gt_bboxes_list,
+                 img_metas,
+                 cfg,
+                 gt_bboxes_ignore_list=None,
+                 gt_labels_list=None,
+                 label_channels=1,
+                 sampling=True,
+                 unmap_outputs=True):
+    """Compute corresponding GT box and classification targets for proposals.
+
+    Args:
+        points_list (list[list]): Multi level points of each image.
+        valid_flag_list (list[list]): Multi level valid flags of each image.
+        gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
+        img_metas (list[dict]): Meta info of each image.
+        cfg (dict): train sample configs.
+
+    Returns:
+        tuple
+    """
+    num_imgs = len(img_metas)
+    assert len(proposals_list) == len(valid_flag_list) == num_imgs
+
+    # points number of multi levels
+    num_level_proposals = [points.size(0) for points in proposals_list[0]]
+
+    # concat all level points and flags to a single tensor
+    for i in range(num_imgs):
+        assert len(proposals_list[i]) == len(valid_flag_list[i])
+        proposals_list[i] = torch.cat(proposals_list[i])
+        valid_flag_list[i] = torch.cat(valid_flag_list[i])
+
+    # compute targets for each image
+    if gt_bboxes_ignore_list is None:
+        gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
+    if gt_labels_list is None:
+        gt_labels_list = [None for _ in range(num_imgs)]
+    (all_labels, all_label_weights, all_bbox_gt, all_proposals,
+     all_proposal_weights, pos_inds_list, neg_inds_list) = multi_apply(
+         point_target_single,
+         proposals_list,
+         valid_flag_list,
+         gt_bboxes_list,
+         gt_bboxes_ignore_list,
+         gt_labels_list,
+         cfg=cfg,
+         label_channels=label_channels,
+         sampling=sampling,
+         unmap_outputs=unmap_outputs)
+    # no valid points
+    if any([labels is None for labels in all_labels]):
+        return None
+    # sampled points of all images
+    num_total_pos = sum([max(inds.numel(), 1) for inds in pos_inds_list])
+    num_total_neg = sum([max(inds.numel(), 1) for inds in neg_inds_list])
+    labels_list = images_to_levels(all_labels, num_level_proposals)
+    label_weights_list = images_to_levels(all_label_weights,
+                                          num_level_proposals)
+    bbox_gt_list = images_to_levels(all_bbox_gt, num_level_proposals)
+    proposals_list = images_to_levels(all_proposals, num_level_proposals)
+    proposal_weights_list = images_to_levels(all_proposal_weights,
+                                             num_level_proposals)
+    return (labels_list, label_weights_list, bbox_gt_list, proposals_list,
+            proposal_weights_list, num_total_pos, num_total_neg)
+
+
+def images_to_levels(target, num_level_grids):
+    """Convert targets by image to targets by feature level.
+
+    [target_img0, target_img1] -> [target_level0, target_level1, ...]
+    """
+    target = torch.stack(target, 0)
+    level_targets = []
+    start = 0
+    for n in num_level_grids:
+        end = start + n
+        level_targets.append(target[:, start:end].squeeze(0))
+        start = end
+    return level_targets
+
+
+def point_target_single(flat_proposals,
+                        valid_flags,
+                        gt_bboxes,
+                        gt_bboxes_ignore,
+                        gt_labels,
+                        cfg,
+                        label_channels=1,
+                        sampling=True,
+                        unmap_outputs=True):
+    inside_flags = valid_flags
+    if not inside_flags.any():
+        return (None, ) * 7
+    # assign gt and sample proposals
+    proposals = flat_proposals[inside_flags, :]
+
+    if sampling:
+        assign_result, sampling_result = assign_and_sample(
+            proposals, gt_bboxes, gt_bboxes_ignore, None, cfg)
+    else:
+        bbox_assigner = build_assigner(cfg.assigner)
+        assign_result = bbox_assigner.assign(proposals, gt_bboxes,
+                                             gt_bboxes_ignore, gt_labels)
+        bbox_sampler = PseudoSampler()
+        sampling_result = bbox_sampler.sample(assign_result, proposals,
+                                              gt_bboxes)
+
+    num_valid_proposals = proposals.shape[0]
+    bbox_gt = proposals.new_zeros([num_valid_proposals, 4])
+    pos_proposals = torch.zeros_like(proposals)
+    proposals_weights = proposals.new_zeros([num_valid_proposals, 4])
+    labels = proposals.new_zeros(num_valid_proposals, dtype=torch.long)
+    label_weights = proposals.new_zeros(num_valid_proposals, dtype=torch.float)
+
+    pos_inds = sampling_result.pos_inds
+    neg_inds = sampling_result.neg_inds
+    if len(pos_inds) > 0:
+        pos_gt_bboxes = sampling_result.pos_gt_bboxes
+        bbox_gt[pos_inds, :] = pos_gt_bboxes
+        pos_proposals[pos_inds, :] = proposals[pos_inds, :]
+        proposals_weights[pos_inds, :] = 1.0
+        if gt_labels is None:
+            labels[pos_inds] = 1
+        else:
+            labels[pos_inds] = gt_labels[sampling_result.pos_assigned_gt_inds]
+        if cfg.pos_weight <= 0:
+            label_weights[pos_inds] = 1.0
+        else:
+            label_weights[pos_inds] = cfg.pos_weight
+    if len(neg_inds) > 0:
+        label_weights[neg_inds] = 1.0
+
+    # map up to original set of proposals
+    if unmap_outputs:
+        num_total_proposals = flat_proposals.size(0)
+        labels = unmap(labels, num_total_proposals, inside_flags)
+        label_weights = unmap(label_weights, num_total_proposals, inside_flags)
+        bbox_gt = unmap(bbox_gt, num_total_proposals, inside_flags)
+        pos_proposals = unmap(pos_proposals, num_total_proposals, inside_flags)
+        proposals_weights = unmap(proposals_weights, num_total_proposals,
+                                  inside_flags)
+
+    return (labels, label_weights, bbox_gt, pos_proposals, proposals_weights,
+            pos_inds, neg_inds)
+
+
+def unmap(data, count, inds, fill=0):
+    """ Unmap a subset of item (data) back to the original set of items (of
+    size count) """
+    if data.dim() == 1:
+        ret = data.new_full((count, ), fill)
+        ret[inds] = data
+    else:
+        new_size = (count, ) + data.size()[1:]
+        ret = data.new_full(new_size, fill)
+        ret[inds, :] = data
+    return ret

mmdet/core/bbox/assigners/__init__.py

@@ -2,7 +2,9 @@ from .approx_max_iou_assigner import ApproxMaxIoUAssigner
 from .assign_result import AssignResult
 from .base_assigner import BaseAssigner
 from .max_iou_assigner import MaxIoUAssigner
+from .point_assigner import PointAssigner
 
 __all__ = [
-    'BaseAssigner', 'MaxIoUAssigner', 'ApproxMaxIoUAssigner', 'AssignResult'
+    'BaseAssigner', 'MaxIoUAssigner', 'ApproxMaxIoUAssigner', 'AssignResult',
+    'PointAssigner'
 ]

mmdet/core/bbox/assigners/point_assigner.py

+import torch
+
+from .assign_result import AssignResult
+from .base_assigner import BaseAssigner
+
+
+class PointAssigner(BaseAssigner):
+    """Assign a corresponding gt bbox or background to each point.
+
+    Each proposals will be assigned with `0`, or a positive integer
+    indicating the ground truth index.
+
+    - 0: negative sample, no assigned gt
+    - positive integer: positive sample, index (1-based) of assigned gt
+
+    """
+
+    def __init__(self, scale=4, pos_num=3):
+        self.scale = scale
+        self.pos_num = pos_num
+
+    def assign(self, points, gt_bboxes, gt_bboxes_ignore=None, gt_labels=None):
+        """Assign gt to points.
+
+        This method assign a gt bbox to every points set, each points set
+        will be assigned with  0, or a positive number.
+        0 means negative sample, positive number is the index (1-based) of
+        assigned gt.
+        The assignment is done in following steps, the order matters.
+
+        1. assign every points to 0
+        2. A point is assigned to some gt bbox if
+            (i) the point is within the k closest points to the gt bbox
+            (ii) the distance between this point and the gt is smaller than
+                other gt bboxes
+
+        Args:
+            points (Tensor): points to be assigned, shape(n, 3) while last
+                dimension stands for (x, y, stride).
+            gt_bboxes (Tensor): Groundtruth boxes, shape (k, 4).
+            gt_bboxes_ignore (Tensor, optional): Ground truth bboxes that are
+                labelled as `ignored`, e.g., crowd boxes in COCO.
+            gt_labels (Tensor, optional): Label of gt_bboxes, shape (k, ).
+
+        Returns:
+            :obj:`AssignResult`: The assign result.
+        """
+        if points.shape[0] == 0 or gt_bboxes.shape[0] == 0:
+            raise ValueError('No gt or bboxes')
+        points_xy = points[:, :2]
+        points_stride = points[:, 2]
+        points_lvl = torch.log2(
+            points_stride).int()  # [3...,4...,5...,6...,7...]
+        lvl_min, lvl_max = points_lvl.min(), points_lvl.max()
+        num_gts, num_points = gt_bboxes.shape[0], points.shape[0]
+
+        # assign gt box
+        gt_bboxes_xy = (gt_bboxes[:, :2] + gt_bboxes[:, 2:]) / 2
+        gt_bboxes_wh = (gt_bboxes[:, 2:] - gt_bboxes[:, :2]).clamp(min=1e-6)
+        scale = self.scale
+        gt_bboxes_lvl = ((torch.log2(gt_bboxes_wh[:, 0] / scale) +
+                          torch.log2(gt_bboxes_wh[:, 1] / scale)) / 2).int()
+        gt_bboxes_lvl = torch.clamp(gt_bboxes_lvl, min=lvl_min, max=lvl_max)
+
+        # stores the assigned gt index of each point
+        assigned_gt_inds = points.new_zeros((num_points, ), dtype=torch.long)
+        # stores the assigned gt dist (to this point) of each point
+        assigned_gt_dist = points.new_full((num_points, ), float('inf'))
+        points_range = torch.arange(points.shape[0])
+
+        for idx in range(num_gts):
+            gt_lvl = gt_bboxes_lvl[idx]
+            # get the index of points in this level
+            lvl_idx = gt_lvl == points_lvl
+            points_index = points_range[lvl_idx]
+            # get the points in this level
+            lvl_points = points_xy[lvl_idx, :]
+            # get the center point of gt
+            gt_point = gt_bboxes_xy[[idx], :]
+            # get width and height of gt
+            gt_wh = gt_bboxes_wh[[idx], :]
+            # compute the distance between gt center and
+            #   all points in this level
+            points_gt_dist = ((lvl_points - gt_point) / gt_wh).norm(dim=1)
+            # find the nearest k points to gt center in this level
+            min_dist, min_dist_index = torch.topk(
+                points_gt_dist, self.pos_num, largest=False)
+            # the index of nearest k points to gt center in this level
+            min_dist_points_index = points_index[min_dist_index]
+            # The less_than_recorded_index stores the index
+            #   of min_dist that is less then the assigned_gt_dist. Where
+            #   assigned_gt_dist stores the dist from previous assigned gt
+            #   (if exist) to each point.
+            less_than_recorded_index = min_dist < assigned_gt_dist[
+                min_dist_points_index]
+            # The min_dist_points_index stores the index of points satisfy:
+            #   (1) it is k nearest to current gt center in this level.
+            #   (2) it is closer to current gt center than other gt center.
+            min_dist_points_index = min_dist_points_index[
+                less_than_recorded_index]
+            # assign the result
+            assigned_gt_inds[min_dist_points_index] = idx + 1
+            assigned_gt_dist[min_dist_points_index] = min_dist[
+                less_than_recorded_index]
+
+        if gt_labels is not None:
+            assigned_labels = assigned_gt_inds.new_zeros((num_points, ))
+            pos_inds = torch.nonzero(assigned_gt_inds > 0).squeeze()
+            if pos_inds.numel() > 0:
+                assigned_labels[pos_inds] = gt_labels[
+                    assigned_gt_inds[pos_inds] - 1]
+        else:
+            assigned_labels = None
+
+        return AssignResult(
+            num_gts, assigned_gt_inds, None, labels=assigned_labels)