add gn configs and models

MODEL_ZOO.md

@@ -168,6 +168,22 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
 - Inference time is reported for batch size = 1 and batch size = 8.
 - The speed difference between VOC and COCO is caused by model parameters and nms.
 
+### Group Normalization (GN)
+
+| Backbone      | model      | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
+|:-------------:|:----------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
+| R-50-FPN (d)  | Mask R-CNN | 2x      | 7.2      | 0.806               | 5.4            | 39.9   | 36.1    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_2x_20180113-86832cf2.pth) |
+| R-50-FPN (d)  | Mask R-CNN | 3x      | 7.2      | 0.806               | 5.4            | 40.2   | 36.5    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_3x_20180113-8e82f48d.pth) |
+| R-101-FPN (d) | Mask R-CNN | 2x      | 9.9      | 0.970               | 4.8            | 41.6   | 37.1    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_gn_2x_20180113-9598649c.pth) |
+| R-101-FPN (d) | Mask R-CNN | 3x      | 9.9      | 0.970               | 4.8            | 41.7   | 37.3    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_gn_3x_20180113-a14ffb96.pth) |
+| R-50-FPN (c)  | Mask R-CNN | 2x      | 7.2      | 0.806               | 5.4            | 39.7   | 35.9    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_contrib_2x_20180113-ec93305c.pth) |
+| R-50-FPN (c)  | Mask R-CNN | 3x      | 7.2      | 0.806               | 5.4            | 40.1   | 36.2    | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_contrib_3x_20180113-9d230cab.pth) |
+
+**Notes:**
+- (d) means pretrained model converted from Detectron, and (c) means the contributed model pretrained by [@thangvubk](https://github.com/thangvubk).
+- The `3x` schedule is epoch [28, 34, 36].
+- The memory is measured with `torch.cuda.max_memory_allocated()` instead of `torch.cuda.max_memory_cached()`. We will update the memory usage of other models in the future.
+
 
 ## Comparison with Detectron
 

configs/mask_rcnn_r101_fpn_gn_2x.py

+# model settings
+normalize = dict(type='GN', num_groups=32, frozen=False)
+
+model = dict(
+    type='MaskRCNN',
+    pretrained='open-mmlab://detectron/resnet101_gn',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        normalize=normalize),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5,
+        normalize=normalize),
+    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='ConvFCBBoxHead',
+        num_shared_convs=4,
+        num_shared_fcs=1,
+        in_channels=256,
+        conv_out_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,
+        normalize=normalize),
+    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,
+        normalize=normalize))
+
+# 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=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+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=[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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/mask_rcnn_r101_fpn_gn_2x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/mask_rcnn_r50_fpn_gn_2x.py

 # model settings
-normalize = dict(
-    type='GN',
-    num_groups=32,
-    frozen=False)
+normalize = dict(type='GN', num_groups=32, frozen=False)
 
 model = dict(
     type='MaskRCNN',
-    pretrained='open-mmlab://contrib/resnet50_gn',
+    pretrained='open-mmlab://detectron/resnet50_gn',
     backbone=dict(
         type='ResNet',
         depth=50,
@@ -114,7 +111,7 @@ test_cfg = dict(
 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)
+    mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
 data = dict(
     imgs_per_gpu=2,
     workers_per_gpu=2,

configs/mask_rcnn_r50_fpn_gn_contrib_2x.py

+# model settings
+normalize = dict(type='GN', num_groups=32, frozen=False)
+
+model = dict(
+    type='MaskRCNN',
+    pretrained='open-mmlab://contrib/resnet50_gn',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        normalize=normalize),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5,
+        normalize=normalize),
+    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='ConvFCBBoxHead',
+        num_shared_convs=4,
+        num_shared_fcs=1,
+        in_channels=256,
+        conv_out_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,
+        normalize=normalize),
+    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,
+        normalize=normalize))
+
+# 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=[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
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/mask_rcnn_r50_fpn_gn_contrib_2x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]