Merge pull request #192 from OceanPang/master

add resnext

MODEL_ZOO.md

@@ -46,6 +46,10 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
 | R-101-FPN | caffe   | 1x      | 7.4      | 0.513               | 11.1           | 59.4   | -        |
 | R-101-FPN | pytorch | 1x      | 8.0      | 0.552               | 11.1           | 58.6   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r101_fpn_1x_20181129-f50da4bd.pth) |
 | R-101-FPN | pytorch | 2x      | 8.0      | 0.552               | 11.1           | 59.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r101_fpn_2x_20181129-e42c6c9a.pth) |
+| X-101-32x4d-FPN | pytorch |1x | 9.9      | 0.691               | 8.3            | 59.4   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_x101_32x4d_fpn_1x_20181218-7e379d26.pth)
+| X-101-32x4d-FPN | pytorch |2x | 9.9      | 0.691               | 8.3            | 59.9   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_x101_32x4d_fpn_2x_20181218-0510af40.pth)
+| X-101-64x4d-FPN | pytorch |1x | 14.6     | 1.032               | 6.2            | 59.8   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_x101_64x4d_fpn_1x_20181218-c1a24f1f.pth)
+| X-101-64x4d-FPN | pytorch |2x | 14.6     | 1.032               | 6.2            | 60.0   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_x101_64x4d_fpn_2x_20181218-c22bdd70.pth)
 
 ### Faster R-CNN
 
@@ -57,6 +61,10 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
 | R-101-FPN | caffe   | 1x      | 7.4      | 0.663               | 8.4           | 38.8   | -        |
 | R-101-FPN | pytorch | 1x      | 8.0      | 0.698               | 8.3           | 38.6   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r101_fpn_1x_20181129-d1468807.pth) |
 | R-101-FPN | pytorch | 2x      | 8.0      | 0.698               | 8.3           | 39.4   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r101_fpn_2x_20181129-73e7ade7.pth) |
+| X-101-32x4d-FPN | pytorch | 1x| 9.9      | 0.842               | 7.0           | 40.2    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_x101_32x4d_fpn_1x_20181218-ad81c133.pth)
+| X-101-32x4d-FPN | pytorch | 2x| 9.9      | 0.842               | 7.0           | 40.5    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_x101_32x4d_fpn_2x_20181218-0ed58946.pth)
+| X-101-64x4d-FPN | pytorch | 1x| 14.1     | 1.181               | 5.2           | 41.3    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_x101_64x4d_fpn_1x_20181218-c9c69c8f.pth)
+| X-101-64x4d-FPN | pytorch | 2x| 14.1     | 1.181               | 5.2           | 40.7    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_x101_64x4d_fpn_2x_20181218-fe94f9b8.pth)
 
 ### Mask R-CNN
 
@@ -68,6 +76,10 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
 | R-101-FPN | caffe   | 1x      | 8.8      | 0.791               | 7.0            | 39.9   | 36.1    | -        |
 | R-101-FPN | pytorch | 1x      | 9.1      | 0.825               | 6.7            | 39.4   | 35.9    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_1x_20181129-34ad1961.pth) |
 | R-101-FPN | pytorch | 2x      | 9.1      | 0.825               | 6.7            | 40.4   | 36.6    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_2x_20181129-a254bdfc.pth) |
+| X-101-32x4d-FPN | pytorch | 1x| 10.9     | 0.972               | 5.8            | 41.2   | 37.2    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_x101_32x4d_fpn_1x_20181218-44e635cc.pth)
+| X-101-64x4d-FPN | pytorch | 2x| 10.9     | 0.972               | 5.8            | 41.4   | 37.1    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_x101_32x4d_fpn_2x_20181218-f023dffa.pth)
+| X-101-32x4d-FPN | pytorch | 1x| 14.1     | 1.302               | 4.7            | 42.2   | 38.1    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_x101_64x4d_fpn_1x_20181218-cb159987.pth)
+| X-101-64x4d-FPN | pytorch | 2x| 14.1     | 1.302               | 4.7            | 42.0   | 37.8    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_x101_64x4d_fpn_2x_20181218-ea936e44.pth)
 
 ### Fast R-CNN (with pre-computed proposals)
 
@@ -96,6 +108,10 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
 | R-101-FPN | caffe   | 1x      | 9.2      | 0.614               | 8.2            | 37.8   | -        |
 | R-101-FPN | pytorch | 1x      | 9.6      | 0.643               | 8.1            | 37.7   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_r101_fpn_1x_20181129-f738a02f.pth) |
 | R-101-FPN | pytorch | 2x      | 9.6      | 0.643               | 8.1            | 38.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_r101_fpn_2x_20181129-f654534b.pth) |
+| X-101-32x4d-FPN | pytorch | 1x| 10.8     | 0.792               | 6.7            | 38.7   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_x101_32x4d_fpn_1x_20181218-c140fb82.pth)
+| X-101-32x4d-FPN | pytorch | 2x| 10.8     | 0.792               | 6.7            | 39.3   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_x101_32x4d_fpn_2x_20181218-605dcd0a.pth)
+| X-101-64x4d-FPN | pytorch | 1x| 14.6     | 1.128               | 5.3            | 40.0   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_x101_64x4d_fpn_1x_20181218-2f6f778b.pth)
+| X-101-64x4d-FPN | pytorch | 2x| 14.6     | 1.128               | 5.3            | 39.6   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_x101_64x4d_fpn_2x_20181218-2f598dc5.pth)
 
 ### Cascade R-CNN
 
@@ -107,6 +123,10 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
 | R-101-FPN | caffe   | 1x      | 8.5      | 0.731               | 7.0            | 42.2   | -        |
 | R-101-FPN | pytorch | 1x      | 8.7      | 0.766               | 6.9            | 42.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r101_fpn_1x_20181129-d64ebac7.pth) |
 | R-101-FPN | pytorch | 20e     | 8.7      | 0.766               | 6.9            | 42.6   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r101_fpn_20e_20181129-b46dcede.pth) |
+| X-101-32x4d-FPN | pytorch | 1x| 10.6     | 0.902               | 5.7            | 43.5   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_x101_32x4d_fpn_1x_20181218-941c0925.pth)
+| X-101-32x4d-FPN | pytorch |20e| 10.6     | 0.902               | 5.7            | 44.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_x101_32x4d_fpn_2x_20181218-28f73c4c.pth)
+| X-101-64x4d-FPN | pytorch | 1x| 14.1     | 1.251               | 4.6            | 44.6   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_x101_64x4d_fpn_1x_20181218-e2dc376a.pth)
+| X-101-64x4d-FPN | pytorch |20e| 14.1     | 1.251               | 4.6            | 44.8   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_x101_64x4d_fpn_2x_20181218-5add321e.pth)
 
 ### Cascade Mask R-CNN
 
@@ -118,7 +138,14 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
 | R-101-FPN | caffe   | 1x      | 10.5     | 1.024               | 5.3            | 43.1   | 37.3    | -        |
 | R-101-FPN | pytorch | 1x      | 10.9     | 1.055               | 5.2            | 42.7   | 37.1    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r101_fpn_1x_20181129-64f00602.pth) |
 | R-101-FPN | pytorch | 20e     | 10.9     | 1.055               | 5.2            | 43.4   | 37.6    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r101_fpn_20e_20181129-cb85151d.pth) |
+| X-101-32x4d-FPN | pytorch | 1x| 12.67    | 1.181               | 4.2            | 44.4   | 38.3    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_x101_32x4d_fpn_1x_20181218-1d944c89.pth)
+| X-101-32x4d-FPN | pytorch |20e| 12.67    | 1.181               | 4.2            | 44.9   | 38.7    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_x101_32x4d_fpn_20e_20181218-761a3473.pth)
+| X-101-64x4d-FPN | pytorch | 1x| 10.87    | 1.125               | 3.6            | 45.5   | 39.2    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_x101_64x4d_fpn_1x_20181218-85953a91.pth)
+| X-101-64x4d-FPN | pytorch |20e| 10.87    | 1.125               | 3.6            | 45.8   | 39.5    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_x101_64x4d_fpn_20e_20181218-630773a7.pth)
 
+**Notes:**
+
+- Cascade Mask R-CNN with X-101-64x4d-FPN was trained using 16 GPU with a batch size of 16 (1 images per GPU).
 
 ## Comparison with Detectron
 

README.md

@@ -58,14 +58,14 @@ Results and models are available in the [Model zoo](MODEL_ZOO.md).
 
 |                    | ResNet   | ResNeXt  | SENet    | VGG      |
 |--------------------|:--------:|:--------:|:--------:|:--------:|
-| RPN                | ✓        | ☐        | ☐        | ✗        |
-| Fast R-CNN         | ✓        | ☐        | ☐        | ✗        |
-| Faster R-CNN       | ✓        | ☐        | ☐        | ✗        |
-| Mask R-CNN         | ✓        | ☐        | ☐        | ✗        |
-| Cascade R-CNN      | ✓        | ☐        | ☐        | ✗        |
-| Cascade Mask R-CNN | ✓        | ☐        | ☐        | ✗        |
+| RPN                | ✓        | ✓        | ☐        | ✗        |
+| Fast R-CNN         | ✓        | ✓        | ☐        | ✗        |
+| Faster R-CNN       | ✓        | ✓        | ☐        | ✗        |
+| Mask R-CNN         | ✓        | ✓        | ☐        | ✗        |
+| Cascade R-CNN      | ✓        | ✓        | ☐        | ✗        |
+| Cascade Mask R-CNN | ✓        | ✓        | ☐        | ✗        |
 | SSD                | ✗        | ✗        | ✗        | ☐        |
-| RetinaNet          | ✓        | ☐        | ☐        | ✗        |
+| RetinaNet          | ✓        | ✓        | ☐        | ✗        |
 
 ## Installation
 

configs/cascade_mask_rcnn_x101_32x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='CascadeRCNN',
+    num_stages=3,
+    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'),
+    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_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=[
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.1, 0.1, 0.2, 0.2],
+            reg_class_agnostic=True),
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.05, 0.05, 0.1, 0.1],
+            reg_class_agnostic=True),
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.033, 0.033, 0.067, 0.067],
+            reg_class_agnostic=True)
+    ],
+    mask_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+        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=81))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=[
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            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,
+                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,
+                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)
+    ],
+    stage_loss_weights=[1, 0.5, 0.25])
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05,
+        nms=dict(type='nms', iou_thr=0.5),
+        max_per_img=100,
+        mask_thr_binary=0.5),
+    keep_all_stages=False)
+# 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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=True,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/cascade_mask_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/cascade_mask_rcnn_x101_64x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='CascadeRCNN',
+    num_stages=3,
+    pretrained='open-mmlab://resnext101_64x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        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,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=[
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.1, 0.1, 0.2, 0.2],
+            reg_class_agnostic=True),
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.05, 0.05, 0.1, 0.1],
+            reg_class_agnostic=True),
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.033, 0.033, 0.067, 0.067],
+            reg_class_agnostic=True)
+    ],
+    mask_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+        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=81))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=[
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            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,
+                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,
+                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)
+    ],
+    stage_loss_weights=[1, 0.5, 0.25])
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05,
+        nms=dict(type='nms', iou_thr=0.5),
+        max_per_img=100,
+        mask_thr_binary=0.5),
+    keep_all_stages=False)
+# 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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=True,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/cascade_mask_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/cascade_rcnn_x101_32x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='CascadeRCNN',
+    num_stages=3,
+    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'),
+    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_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=[
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.1, 0.1, 0.2, 0.2],
+            reg_class_agnostic=True),
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.05, 0.05, 0.1, 0.1],
+            reg_class_agnostic=True),
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.033, 0.033, 0.067, 0.067],
+            reg_class_agnostic=True)
+    ])
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=[
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False),
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.6,
+                neg_iou_thr=0.6,
+                min_pos_iou=0.6,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False),
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.7,
+                min_pos_iou=0.7,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)
+    ],
+    stage_loss_weights=[1, 0.5, 0.25])
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100),
+    keep_all_stages=False)
+# 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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/cascade_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/cascade_rcnn_x101_64x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='CascadeRCNN',
+    num_stages=3,
+    pretrained='open-mmlab://resnext101_64x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        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,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=[
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.1, 0.1, 0.2, 0.2],
+            reg_class_agnostic=True),
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.05, 0.05, 0.1, 0.1],
+            reg_class_agnostic=True),
+        dict(
+            type='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=81,
+            target_means=[0., 0., 0., 0.],
+            target_stds=[0.033, 0.033, 0.067, 0.067],
+            reg_class_agnostic=True)
+    ])
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=[
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False),
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.6,
+                neg_iou_thr=0.6,
+                min_pos_iou=0.6,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False),
+        dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.7,
+                min_pos_iou=0.7,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)
+    ],
+    stage_loss_weights=[1, 0.5, 0.25])
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100),
+    keep_all_stages=False)
+# 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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/cascade_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/faster_rcnn_x101_32x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='FasterRCNN',
+    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'),
+    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_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=dict(
+        type='SharedFCBBoxHead',
+        num_fcs=2,
+        in_channels=256,
+        fc_out_channels=1024,
+        roi_feat_size=7,
+        num_classes=81,
+        target_means=[0., 0., 0., 0.],
+        target_stds=[0.1, 0.1, 0.2, 0.2],
+        reg_class_agnostic=False))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.5,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=512,
+            pos_fraction=0.25,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=True),
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100)
+    # soft-nms is also supported for rcnn testing
+    # e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
+)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/faster_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/faster_rcnn_x101_64x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='FasterRCNN',
+    pretrained='open-mmlab://resnext101_64x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        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,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=dict(
+        type='SharedFCBBoxHead',
+        num_fcs=2,
+        in_channels=256,
+        fc_out_channels=1024,
+        roi_feat_size=7,
+        num_classes=81,
+        target_means=[0., 0., 0., 0.],
+        target_stds=[0.1, 0.1, 0.2, 0.2],
+        reg_class_agnostic=False))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.5,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=512,
+            pos_fraction=0.25,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=True),
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100)
+    # soft-nms is also supported for rcnn testing
+    # e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
+)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/faster_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/mask_rcnn_x101_32x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='MaskRCNN',
+    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'),
+    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_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=dict(
+        type='SharedFCBBoxHead',
+        num_fcs=2,
+        in_channels=256,
+        fc_out_channels=1024,
+        roi_feat_size=7,
+        num_classes=81,
+        target_means=[0., 0., 0., 0.],
+        target_stds=[0.1, 0.1, 0.2, 0.2],
+        reg_class_agnostic=False),
+    mask_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+        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=81))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.5,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=512,
+            pos_fraction=0.25,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=True),
+        mask_size=28,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05,
+        nms=dict(type='nms', iou_thr=0.5),
+        max_per_img=100,
+        mask_thr_binary=0.5))
+# 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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/mask_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/mask_rcnn_x101_64x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='MaskRCNN',
+    pretrained='open-mmlab://resnext101_64x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        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,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    bbox_head=dict(
+        type='SharedFCBBoxHead',
+        num_fcs=2,
+        in_channels=256,
+        fc_out_channels=1024,
+        roi_feat_size=7,
+        num_classes=81,
+        target_means=[0., 0., 0., 0.],
+        target_stds=[0.1, 0.1, 0.2, 0.2],
+        reg_class_agnostic=False),
+    mask_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+        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=81))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.5,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=512,
+            pos_fraction=0.25,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=True),
+        mask_size=28,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.05,
+        nms=dict(type='nms', iou_thr=0.5),
+        max_per_img=100,
+        mask_thr_binary=0.5))
+# 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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/mask_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/retinanet_x101_32x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='RetinaNet',
+    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'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5),
+    bbox_head=dict(
+        type='RetinaHead',
+        num_classes=81,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        octave_base_scale=4,
+        scales_per_octave=3,
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[8, 16, 32, 64, 128],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0]))
+# training and testing settings
+train_cfg = dict(
+    assigner=dict(
+        type='MaxIoUAssigner',
+        pos_iou_thr=0.5,
+        neg_iou_thr=0.4,
+        min_pos_iou=0,
+        ignore_iof_thr=-1),
+    smoothl1_beta=0.11,
+    gamma=2.0,
+    alpha=0.25,
+    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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=False,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=False,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=False,
+        with_label=False,
+        test_mode=True))
+# 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/retinanet_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/retinanet_x101_64x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='RetinaNet',
+    pretrained='open-mmlab://resnext101_64x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        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),
+    bbox_head=dict(
+        type='RetinaHead',
+        num_classes=81,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        octave_base_scale=4,
+        scales_per_octave=3,
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[8, 16, 32, 64, 128],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0]))
+# training and testing settings
+train_cfg = dict(
+    assigner=dict(
+        type='MaxIoUAssigner',
+        pos_iou_thr=0.5,
+        neg_iou_thr=0.4,
+        min_pos_iou=0,
+        ignore_iof_thr=-1),
+    smoothl1_beta=0.11,
+    gamma=2.0,
+    alpha=0.25,
+    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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=False,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=False,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=False,
+        with_label=False,
+        test_mode=True))
+# 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/retinanet_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/rpn_x101_32x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='RPN',
+    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'),
+    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_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False))
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0))
+# 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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=False,
+        with_label=False),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=False,
+        with_label=False),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+# runner configs
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/rpn_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/rpn_x101_64x4d_fpn_1x.py

+# model settings
+model = dict(
+    type='RPN',
+    pretrained='open-mmlab://resnext101_64x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        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,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_scales=[8],
+        anchor_ratios=[0.5, 1.0, 2.0],
+        anchor_strides=[4, 8, 16, 32, 64],
+        target_means=[.0, .0, .0, .0],
+        target_stds=[1.0, 1.0, 1.0, 1.0],
+        use_sigmoid_cls=True))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.7,
+            neg_iou_thr=0.3,
+            min_pos_iou=0.3,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='RandomSampler',
+            num=256,
+            pos_fraction=0.5,
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False),
+        allowed_border=0,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False))
+test_cfg = dict(
+    rpn=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        nms_thr=0.7,
+        min_bbox_size=0))
+# 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)
+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/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=False,
+        with_crowd=False,
+        with_label=False),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_crowd=False,
+        with_label=False),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=False,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+# runner configs
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/rpn_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

mmdet/models/backbones/__init__.py

 from .resnet import ResNet
+from .resnext import ResNeXt
 
-__all__ = ['ResNet']
+__all__ = ['ResNet', 'ResNeXt']

mmdet/models/backbones/resnet.py

@@ -42,7 +42,7 @@ class BasicBlock(nn.Module):
         assert not with_cp
 
     def forward(self, x):
-        residual = x
+        identity = x
 
         out = self.conv1(x)
         out = self.bn1(out)
@@ -52,9 +52,9 @@ class BasicBlock(nn.Module):
         out = self.bn2(out)
 
         if self.downsample is not None:
-            residual = self.downsample(x)
+            identity = self.downsample(x)
 
-        out += residual
+        out += identity
         out = self.relu(out)
 
         return out
@@ -71,25 +71,31 @@ class Bottleneck(nn.Module):
                  downsample=None,
                  style='pytorch',
                  with_cp=False):
-        """Bottleneck block.
+        """Bottleneck block for ResNet.
         If style is "pytorch", the stride-two layer is the 3x3 conv layer,
         if it is "caffe", the stride-two layer is the first 1x1 conv layer.
         """
         super(Bottleneck, self).__init__()
         assert style in ['pytorch', 'caffe']
+        self.inplanes = inplanes
+        self.planes = planes
         if style == 'pytorch':
-            conv1_stride = 1
-            conv2_stride = stride
+            self.conv1_stride = 1
+            self.conv2_stride = stride
         else:
-            conv1_stride = stride
-            conv2_stride = 1
+            self.conv1_stride = stride
+            self.conv2_stride = 1
         self.conv1 = nn.Conv2d(
-            inplanes, planes, kernel_size=1, stride=conv1_stride, bias=False)
+            inplanes,
+            planes,
+            kernel_size=1,
+            stride=self.conv1_stride,
+            bias=False)
         self.conv2 = nn.Conv2d(
             planes,
             planes,
             kernel_size=3,
-            stride=conv2_stride,
+            stride=self.conv2_stride,
             padding=dilation,
             dilation=dilation,
             bias=False)
@@ -108,7 +114,7 @@ class Bottleneck(nn.Module):
     def forward(self, x):
 
         def _inner_forward(x):
-            residual = x
+            identity = x
 
             out = self.conv1(x)
             out = self.bn1(out)
@@ -122,9 +128,9 @@ class Bottleneck(nn.Module):
             out = self.bn3(out)
 
             if self.downsample is not None:
-                residual = self.downsample(x)
+                identity = self.downsample(x)
 
-            out += residual
+            out += identity
 
             return out
 
@@ -219,20 +225,24 @@ class ResNet(nn.Module):
         super(ResNet, self).__init__()
         if depth not in self.arch_settings:
             raise KeyError('invalid depth {} for resnet'.format(depth))
+        self.depth = depth
+        self.num_stages = num_stages
         assert num_stages >= 1 and num_stages <= 4
-        block, stage_blocks = self.arch_settings[depth]
-        stage_blocks = stage_blocks[:num_stages]
+        self.strides = strides
+        self.dilations = dilations
         assert len(strides) == len(dilations) == num_stages
-        assert max(out_indices) < num_stages
-
         self.out_indices = out_indices
+        assert max(out_indices) < num_stages
         self.style = style
         self.frozen_stages = frozen_stages
         self.bn_eval = bn_eval
         self.bn_frozen = bn_frozen
         self.with_cp = with_cp
 
+        self.block, stage_blocks = self.arch_settings[depth]
+        self.stage_blocks = stage_blocks[:num_stages]
         self.inplanes = 64
+
         self.conv1 = nn.Conv2d(
             3, 64, kernel_size=7, stride=2, padding=3, bias=False)
         self.bn1 = nn.BatchNorm2d(64)
@@ -240,12 +250,12 @@ class ResNet(nn.Module):
         self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
 
         self.res_layers = []
-        for i, num_blocks in enumerate(stage_blocks):
+        for i, num_blocks in enumerate(self.stage_blocks):
             stride = strides[i]
             dilation = dilations[i]
             planes = 64 * 2**i
             res_layer = make_res_layer(
-                block,
+                self.block,
                 self.inplanes,
                 planes,
                 num_blocks,
@@ -253,12 +263,13 @@ class ResNet(nn.Module):
                 dilation=dilation,
                 style=self.style,
                 with_cp=with_cp)
-            self.inplanes = planes * block.expansion
+            self.inplanes = planes * self.block.expansion
             layer_name = 'layer{}'.format(i + 1)
             self.add_module(layer_name, res_layer)
             self.res_layers.append(layer_name)
 
-        self.feat_dim = block.expansion * 64 * 2**(len(stage_blocks) - 1)
+        self.feat_dim = self.block.expansion * 64 * 2**(
+            len(self.stage_blocks) - 1)
 
     def init_weights(self, pretrained=None):
         if isinstance(pretrained, str):

mmdet/models/backbones/resnext.py

+import math
+
+import torch.nn as nn
+
+from .resnet import ResNet
+from .resnet import Bottleneck as _Bottleneck
+
+
+class Bottleneck(_Bottleneck):
+
+    def __init__(self, *args, groups=1, base_width=4, **kwargs):
+        """Bottleneck block for ResNeXt.
+        If style is "pytorch", the stride-two layer is the 3x3 conv layer,
+        if it is "caffe", the stride-two layer is the first 1x1 conv layer.
+        """
+        super(Bottleneck, self).__init__(*args, **kwargs)
+
+        if groups == 1:
+            width = self.planes
+        else:
+            width = math.floor(self.planes * (base_width / 64)) * groups
+
+        self.conv1 = nn.Conv2d(
+            self.inplanes,
+            width,
+            kernel_size=1,
+            stride=self.conv1_stride,
+            bias=False)
+        self.bn1 = nn.BatchNorm2d(width)
+        self.conv2 = nn.Conv2d(
+            width,
+            width,
+            kernel_size=3,
+            stride=self.conv2_stride,
+            padding=self.dilation,
+            dilation=self.dilation,
+            groups=groups,
+            bias=False)
+        self.bn2 = nn.BatchNorm2d(width)
+        self.conv3 = nn.Conv2d(
+            width, self.planes * self.expansion, kernel_size=1, bias=False)
+        self.bn3 = nn.BatchNorm2d(self.planes * self.expansion)
+
+
+def make_res_layer(block,
+                   inplanes,
+                   planes,
+                   blocks,
+                   stride=1,
+                   dilation=1,
+                   groups=1,
+                   base_width=4,
+                   style='pytorch',
+                   with_cp=False):
+    downsample = None
+    if stride != 1 or inplanes != planes * block.expansion:
+        downsample = nn.Sequential(
+            nn.Conv2d(
+                inplanes,
+                planes * block.expansion,
+                kernel_size=1,
+                stride=stride,
+                bias=False),
+            nn.BatchNorm2d(planes * block.expansion),
+        )
+
+    layers = []
+    layers.append(
+        block(
+            inplanes,
+            planes,
+            stride=stride,
+            dilation=dilation,
+            downsample=downsample,
+            groups=groups,
+            base_width=base_width,
+            style=style,
+            with_cp=with_cp))
+    inplanes = planes * block.expansion
+    for i in range(1, blocks):
+        layers.append(
+            block(
+                inplanes,
+                planes,
+                stride=1,
+                dilation=dilation,
+                groups=groups,
+                base_width=base_width,
+                style=style,
+                with_cp=with_cp))
+
+    return nn.Sequential(*layers)
+
+
+class ResNeXt(ResNet):
+    """ResNeXt backbone.
+
+    Args:
+        depth (int): Depth of resnet, from {18, 34, 50, 101, 152}.
+        num_stages (int): Resnet stages, normally 4.
+        groups (int): Group of resnext.
+        base_width (int): Base width of resnext.
+        strides (Sequence[int]): Strides of the first block of each stage.
+        dilations (Sequence[int]): Dilation of each stage.
+        out_indices (Sequence[int]): Output from which stages.
+        style (str): `pytorch` or `caffe`. If set to "pytorch", the stride-two
+            layer is the 3x3 conv layer, otherwise the stride-two layer is
+            the first 1x1 conv layer.
+        frozen_stages (int): Stages to be frozen (all param fixed). -1 means
+            not freezing any parameters.
+        bn_eval (bool): Whether to set BN layers to eval mode, namely, freeze
+            running stats (mean and var).
+        bn_frozen (bool): Whether to freeze weight and bias of BN layers.
+        with_cp (bool): Use checkpoint or not. Using checkpoint will save some
+            memory while slowing down the training speed.
+    """
+
+    arch_settings = {
+        50: (Bottleneck, (3, 4, 6, 3)),
+        101: (Bottleneck, (3, 4, 23, 3)),
+        152: (Bottleneck, (3, 8, 36, 3))
+    }
+
+    def __init__(self, groups=1, base_width=4, **kwargs):
+        super(ResNeXt, self).__init__(**kwargs)
+        self.groups = groups
+        self.base_width = base_width
+
+        self.inplanes = 64
+        self.res_layers = []
+        for i, num_blocks in enumerate(self.stage_blocks):
+            stride = self.strides[i]
+            dilation = self.dilations[i]
+            planes = 64 * 2**i
+            res_layer = make_res_layer(
+                self.block,
+                self.inplanes,
+                planes,
+                num_blocks,
+                stride=stride,
+                dilation=dilation,
+                groups=self.groups,
+                base_width=self.base_width,
+                style=self.style,
+                with_cp=self.with_cp)
+            self.inplanes = planes * self.block.expansion
+            layer_name = 'layer{}'.format(i + 1)
+            self.add_module(layer_name, res_layer)
+            self.res_layers.append(layer_name)

tools/train.py

@@ -14,6 +14,8 @@ def parse_args():
     parser = argparse.ArgumentParser(description='Train a detector')
     parser.add_argument('config', help='train config file path')
     parser.add_argument('--work_dir', help='the dir to save logs and models')
+    parser.add_argument(
+        '--resume_from', help='the checkpoint file to resume from')
     parser.add_argument(
         '--validate',
         action='store_true',
@@ -43,6 +45,8 @@ def main():
     # update configs according to CLI args
     if args.work_dir is not None:
         cfg.work_dir = args.work_dir
+    if args.resume_from is not None:
+        cfg.resume_from = args.resume_from
     cfg.gpus = args.gpus
     if cfg.checkpoint_config is not None:
         # save mmdet version in checkpoints as meta data
@@ -67,6 +71,7 @@ def main():
 
     model = build_detector(
         cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
+
     train_dataset = get_dataset(cfg.data.train)
     train_detector(
         model,