diff --git a/MODEL_ZOO.md b/MODEL_ZOO.md
index ea25a021ce708a4eb6b2fc45e8df2cd842c9efd9..7526d8309fdf50ee5dba6dec870c4568dfa46eb1 100644
--- a/MODEL_ZOO.md
+++ b/MODEL_ZOO.md
@@ -41,35 +41,50 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | AR1000 | Download |
|:--------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:|
| R-50-FPN | caffe | 1x | 4.5 | 0.379 | 14.4 | 58.2 | - |
-| R-50-FPN | pytorch | 1x | 4.8 | 0.407 | 14.5 | 57.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_fpn_1x_20181010-4a9c0712.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/rpn_r50_fpn_1x_20181010_results.pkl.json) |
-| R-50-FPN | pytorch | 2x | 4.8 | 0.407 | 14.5 | 57.6 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_fpn_2x_20181010-88a4a471.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/rpn_r50_fpn_2x_20181010_results.pkl.json) |
+| R-50-FPN | pytorch | 1x | 4.8 | 0.407 | 14.5 | 57.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_fpn_1x_20181010-4a9c0712.pth) |
+| R-50-FPN | pytorch | 2x | 4.8 | 0.407 | 14.5 | 57.6 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_fpn_2x_20181010-88a4a471.pth) |
+| 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) |
### Faster R-CNN
| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
|:--------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:|
| R-50-FPN | caffe | 1x | 4.9 | 0.525 | 10.0 | 36.7 | - |
-| R-50-FPN | pytorch | 1x | 5.1 | 0.554 | 9.9 | 36.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/faster_rcnn_r50_fpn_1x_20181010_results.pkl.json) |
-| R-50-FPN | pytorch | 2x | 5.1 | 0.554 | 9.9 | 37.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_fpn_2x_20181010-443129e1.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/faster_rcnn_r50_fpn_2x_20181010_results.pkl.json) |
+| R-50-FPN | pytorch | 1x | 5.1 | 0.554 | 9.9 | 36.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth) |
+| R-50-FPN | pytorch | 2x | 5.1 | 0.554 | 9.9 | 37.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_fpn_2x_20181010-443129e1.pth) |
+| 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) |
### Mask R-CNN
| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
|:--------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
| R-50-FPN | caffe | 1x | 5.9 | 0.658 | 7.7 | 37.5 | 34.4 | - |
-| R-50-FPN | pytorch | 1x | 5.8 | 0.690 | 7.7 | 37.3 | 34.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_1x_20181010-069fa190.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/mask_rcnn_r50_fpn_1x_20181010_results.pkl.json) |
-| R-50-FPN | pytorch | 2x | 5.8 | 0.690 | 7.7 | 38.6 | 35.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_2x_20181010-41d35c05.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/mask_rcnn_r50_fpn_2x_20181010_results.pkl.json) |
+| R-50-FPN | pytorch | 1x | 5.8 | 0.690 | 7.7 | 37.3 | 34.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_1x_20181010-069fa190.pth) |
+| R-50-FPN | pytorch | 2x | 5.8 | 0.690 | 7.7 | 38.6 | 35.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_2x_20181010-41d35c05.pth) |
+| 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) |
### Fast R-CNN (with pre-computed proposals)
| Backbone | Style | Type | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
|:--------:|:-------:|:------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
-| R-50-FPN | caffe | Faster | 1x | 3.5 | 0.35 | 14.6 | 36.6 | - | - |
-| R-50-FPN | pytorch | Faster | 1x | 4.0 | 0.38 | 14.5 | 35.8 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_fpn_1x_20181010-08160859.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/fast_rcnn_r50_fpn_1x_20181010_results.pkl.json) |
-| R-50-FPN | pytorch | Faster | 2x | 4.0 | 0.38 | 14.5 | 37.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_fpn_2x_20181010-d263ada5.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/fast_rcnn_r50_fpn_2x_20181010_results.pkl.json) |
-| R-50-FPN | caffe | Mask | 1x | 5.4 | 0.47 | 10.7 | 37.3 | 34.5 | - |
-| R-50-FPN | pytorch | Mask | 1x | 5.3 | 0.50 | 10.6 | 36.8 | 34.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_fpn_1x_20181010-e030a38f.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/fast_mask_rcnn_r50_fpn_1x_20181010_results.pkl.json) |
-| R-50-FPN | pytorch | Mask | 2x | 5.3 | 0.50 | 10.6 | 37.9 | 34.8 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_fpn_2x_20181010-5048cb03.pth) \| [result](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/results/fast_mask_rcnn_r50_fpn_2x_20181010_results.pkl.json) |
+| R-50-FPN | caffe | Faster | 1x | 3.5 | 0.348 | 14.6 | 36.6 | - | - |
+| R-50-FPN | pytorch | Faster | 1x | 4.0 | 0.375 | 14.5 | 35.8 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_fpn_1x_20181010-08160859.pth) |
+| R-50-FPN | pytorch | Faster | 2x | 4.0 | 0.375 | 14.5 | 37.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_fpn_2x_20181010-d263ada5.pth) |
+| R-101-FPN| caffe | Faster | 1x | 7.1 | 0.484 | 11.9 | 38.4 | - | - |
+| R-101-FPN| pytorch | Faster | 1x | 7.6 | 0.540 | 11.8 | 38.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r101_fpn_1x_20181129-ffaa2eb0.pth) |
+| R-101-FPN| pytorch | Faster | 2x | 7.6 | 0.540 | 11.8 | 38.8 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r101_fpn_2x_20181129-9dba92ce.pth) |
+| R-50-FPN | caffe | Mask | 1x | 5.4 | 0.473 | 10.7 | 37.3 | 34.5 | - |
+| R-50-FPN | pytorch | Mask | 1x | 5.3 | 0.504 | 10.6 | 36.8 | 34.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_fpn_1x_20181010-e030a38f.pth) |
+| R-50-FPN | pytorch | Mask | 2x | 5.3 | 0.504 | 10.6 | 37.9 | 34.8 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_fpn_2x_20181010-5048cb03.pth) |
+| R-101-FPN| caffe | Mask | 1x | 8.6 | 0.607 | 9.5 | 39.4 | 36.1 | - |
+| R-101-FPN| pytorch | Mask | 1x | 9.0 | 0.656 | 9.3 | 38.9 | 35.8 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r101_fpn_1x_20181129-2273fa9b.pth) |
+| R-101-FPN| pytorch | Mask | 2x | 9.0 | 0.656 | 9.3 | 39.9 | 36.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r101_fpn_2x_20181129-bf63ec5e.pth) |
### RetinaNet
@@ -78,6 +93,9 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
| R-50-FPN | caffe | 1x | 6.7 | 0.468 | 9.4 | 35.8 | - |
| R-50-FPN | pytorch | 1x | 6.9 | 0.496 | 9.1 | 35.6 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_r50_fpn_1x_20181125-3d3c2142.pth) |
| R-50-FPN | pytorch | 2x | 6.9 | 0.496 | 9.1 | 36.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_r50_fpn_2x_20181125-e0dbec97.pth) |
+| 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) |
### Cascade R-CNN
@@ -86,6 +104,9 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
| R-50-FPN | caffe | 1x | 5.0 | 0.592 | 8.1 | 40.3 | - |
| R-50-FPN | pytorch | 1x | 5.5 | 0.622 | 8.0 | 40.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r50_fpn_1x_20181123-b1987c4a.pth) |
| R-50-FPN | pytorch | 20e | 5.5 | 0.622 | 8.0 | 41.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r50_fpn_20e_20181123-db483a09.pth) |
+| 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) |
### Cascade Mask R-CNN
@@ -94,6 +115,9 @@ We released RPN, Faster R-CNN and Mask R-CNN models in the first version. More m
| R-50-FPN | caffe | 1x | 7.5 | 0.880 | 5.8 | 41.0 | 35.6 | - |
| R-50-FPN | pytorch | 1x | 7.6 | 0.910 | 5.7 | 41.3 | 35.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r50_fpn_1x_20181123-88b170c9.pth) |
| R-50-FPN | pytorch | 20e | 7.6 | 0.910 | 5.7 | 42.4 | 36.6 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r50_fpn_20e_20181123-6e0c9713.pth) |
+| 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) |
## Comparison with Detectron
diff --git a/configs/cascade_mask_rcnn_r101_fpn_1x.py b/configs/cascade_mask_rcnn_r101_fpn_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..2cb289e096638bcbee8f42626bb5cfc025713fb6
--- /dev/null
+++ b/configs/cascade_mask_rcnn_r101_fpn_1x.py
@@ -0,0 +1,227 @@
+# model settings
+model = dict(
+ type='CascadeRCNN',
+ num_stages=3,
+ pretrained='modelzoo://resnet101',
+ backbone=dict(
+ type='ResNet',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ 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(
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ allowed_border=0,
+ pos_weight=-1,
+ smoothl1_beta=1 / 9.0,
+ debug=False),
+ rcnn=[
+ dict(
+ assigner=dict(
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ pos_iou_thr=0.6,
+ neg_iou_thr=0.6,
+ min_pos_iou=0.6,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.7,
+ min_pos_iou=0.7,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ 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_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/cascade_rcnn_r101_fpn_1x.py b/configs/cascade_rcnn_r101_fpn_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..e30370bbe85cb6460c2e0be9c3edb04bde1a7fb2
--- /dev/null
+++ b/configs/cascade_rcnn_r101_fpn_1x.py
@@ -0,0 +1,210 @@
+# model settings
+model = dict(
+ type='CascadeRCNN',
+ num_stages=3,
+ pretrained='modelzoo://resnet101',
+ backbone=dict(
+ type='ResNet',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ 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(
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ allowed_border=0,
+ pos_weight=-1,
+ smoothl1_beta=1 / 9.0,
+ debug=False),
+ rcnn=[
+ dict(
+ assigner=dict(
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ pos_iou_thr=0.6,
+ neg_iou_thr=0.6,
+ min_pos_iou=0.6,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.7,
+ min_pos_iou=0.7,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ 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_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/fast_mask_rcnn_r101_fpn_1x.py b/configs/fast_mask_rcnn_r101_fpn_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..342d775ec62b542a0e5fed90cd62d65e3d05c2d3
--- /dev/null
+++ b/configs/fast_mask_rcnn_r101_fpn_1x.py
@@ -0,0 +1,137 @@
+# model settings
+model = dict(
+ type='FastRCNN',
+ pretrained='modelzoo://resnet101',
+ backbone=dict(
+ type='ResNet',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ num_outs=5),
+ 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(
+ rcnn=dict(
+ assigner=dict(
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False))
+test_cfg = dict(
+ 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,
+ proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
+ 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,
+ proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
+ 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,
+ proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
+ 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/fast_mask_rcnn_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/fast_rcnn_r101_fpn_1x.py b/configs/fast_rcnn_r101_fpn_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..66b7e8c942a2dc49bb0432ae362c921273c0dac3
--- /dev/null
+++ b/configs/fast_rcnn_r101_fpn_1x.py
@@ -0,0 +1,122 @@
+# model settings
+model = dict(
+ type='FastRCNN',
+ pretrained='modelzoo://resnet101',
+ backbone=dict(
+ type='ResNet',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ num_outs=5),
+ 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(
+ rcnn=dict(
+ assigner=dict(
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ pos_weight=-1,
+ debug=False))
+test_cfg = dict(
+ rcnn=dict(
+ 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,
+ proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
+ 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,
+ proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
+ 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,
+ proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
+ 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/fast_rcnn_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/faster_rcnn_r101_fpn_1x.py b/configs/faster_rcnn_r101_fpn_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..49813d180781aaa4a5c822fbc5a5889ff5fb708f
--- /dev/null
+++ b/configs/faster_rcnn_r101_fpn_1x.py
@@ -0,0 +1,156 @@
+# model settings
+model = dict(
+ type='FasterRCNN',
+ pretrained='modelzoo://resnet101',
+ backbone=dict(
+ type='ResNet',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ 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(
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ allowed_border=0,
+ pos_weight=-1,
+ smoothl1_beta=1 / 9.0,
+ debug=False),
+ rcnn=dict(
+ assigner=dict(
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ 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_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/mask_rcnn_r101_fpn_1x.py b/configs/mask_rcnn_r101_fpn_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..65a93e28e6d18ed94c8135b1b525e3c18bb7c981
--- /dev/null
+++ b/configs/mask_rcnn_r101_fpn_1x.py
@@ -0,0 +1,168 @@
+# model settings
+model = dict(
+ type='MaskRCNN',
+ pretrained='modelzoo://resnet101',
+ backbone=dict(
+ type='ResNet',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ 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(
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ allowed_border=0,
+ pos_weight=-1,
+ smoothl1_beta=1 / 9.0,
+ debug=False),
+ rcnn=dict(
+ assigner=dict(
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ 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_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/retinanet_r101_fpn_1x.py b/configs/retinanet_r101_fpn_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..fd4dd9a6d65d8cb700749a37b23c290570c1af17
--- /dev/null
+++ b/configs/retinanet_r101_fpn_1x.py
@@ -0,0 +1,116 @@
+# model settings
+model = dict(
+ type='RetinaNet',
+ pretrained='modelzoo://resnet101',
+ backbone=dict(
+ type='ResNet',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ start_level=1,
+ add_extra_convs=True,
+ num_outs=5),
+ 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(
+ 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_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/rpn_r101_fpn_1x.py b/configs/rpn_r101_fpn_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..90f260d60f81e0fce371156b252f59936cb1f6a0
--- /dev/null
+++ b/configs/rpn_r101_fpn_1x.py
@@ -0,0 +1,121 @@
+# model settings
+model = dict(
+ type='RPN',
+ pretrained='modelzoo://resnet101',
+ backbone=dict(
+ type='ResNet',
+ depth=101,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ 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(
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False,
+ pos_balance_sampling=False,
+ neg_balance_thr=0),
+ 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)]