Merge pull request #20 from open-mmlab/dev

Initial public release

.gitignore

@@ -102,3 +102,8 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+
+# cython generated cpp
+mmdet/ops/nms/*.cpp
+mmdet/version.py
+data

.travis.yml

+dist: trusty
+language: python
+
+install:
+  - pip install flake8
+
+python:
+  - "2.7"
+  - "3.5"
+  - "3.6"
+
+script:
+  - flake8
\ No newline at end of file

compile.sh

+#!/usr/bin/env bash
+
+PYTHON=${PYTHON:-"python"}
+
+echo "Building roi align op..."
+cd mmdet/ops/roi_align
+if [ -d "build" ]; then
+    rm -r build
+fi
+$PYTHON setup.py build_ext --inplace
+
+echo "Building roi pool op..."
+cd ../roi_pool
+if [ -d "build" ]; then
+    rm -r build
+fi
+$PYTHON setup.py build_ext --inplace
+
+echo "Building nms op..."
+cd ../nms
+make clean
+make PYTHON=${PYTHON}

configs/fast_mask_rcnn_r50_fpn_1x.py

+# model settings
+model = dict(
+    type='FastRCNN',
+    pretrained='modelzoo://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        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='SharedFCRoIHead',
+        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(
+        mask_size=28,
+        pos_iou_thr=0.5,
+        neg_iou_thr=0.5,
+        crowd_thr=1.1,
+        roi_batch_size=512,
+        add_gt_as_proposals=True,
+        pos_fraction=0.25,
+        pos_balance_sampling=False,
+        neg_pos_ub=512,
+        neg_balance_thr=0,
+        min_pos_iou=0.5,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(
+    rcnn=dict(
+        score_thr=0.05, max_per_img=100, nms_thr=0.5, 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_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/fast_rcnn_r50_fpn_1x.py

+# model settings
+model = dict(
+    type='FastRCNN',
+    pretrained='modelzoo://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        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='SharedFCRoIHead',
+        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(
+        pos_iou_thr=0.5,
+        neg_iou_thr=0.5,
+        crowd_thr=1.1,
+        roi_batch_size=512,
+        add_gt_as_proposals=True,
+        pos_fraction=0.25,
+        pos_balance_sampling=False,
+        neg_pos_ub=512,
+        neg_balance_thr=0,
+        min_pos_iou=0.5,
+        pos_weight=-1,
+        debug=False))
+test_cfg = dict(rcnn=dict(score_thr=0.05, max_per_img=100, nms_thr=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=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_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/faster_rcnn_r50_fpn_1x.py

+# model settings
+model = dict(
+    type='FasterRCNN',
+    pretrained='modelzoo://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        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='SharedFCRoIHead',
+        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(
+        pos_fraction=0.5,
+        pos_balance_sampling=False,
+        neg_pos_ub=256,
+        allowed_border=0,
+        crowd_thr=1.1,
+        anchor_batch_size=256,
+        pos_iou_thr=0.7,
+        neg_iou_thr=0.3,
+        neg_balance_thr=0,
+        min_pos_iou=0.3,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=dict(
+        pos_iou_thr=0.5,
+        neg_iou_thr=0.5,
+        crowd_thr=1.1,
+        roi_batch_size=512,
+        add_gt_as_proposals=True,
+        pos_fraction=0.25,
+        pos_balance_sampling=False,
+        neg_pos_ub=512,
+        neg_balance_thr=0,
+        min_pos_iou=0.5,
+        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, max_per_img=100, nms_thr=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=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_r50_fpn_1x.py

+# model settings
+model = dict(
+    type='MaskRCNN',
+    pretrained='modelzoo://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        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='SharedFCRoIHead',
+        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(
+        pos_fraction=0.5,
+        pos_balance_sampling=False,
+        neg_pos_ub=256,
+        allowed_border=0,
+        crowd_thr=1.1,
+        anchor_batch_size=256,
+        pos_iou_thr=0.7,
+        neg_iou_thr=0.3,
+        neg_balance_thr=0,
+        min_pos_iou=0.3,
+        pos_weight=-1,
+        smoothl1_beta=1 / 9.0,
+        debug=False),
+    rcnn=dict(
+        mask_size=28,
+        pos_iou_thr=0.5,
+        neg_iou_thr=0.5,
+        crowd_thr=1.1,
+        roi_batch_size=512,
+        add_gt_as_proposals=True,
+        pos_fraction=0.25,
+        pos_balance_sampling=False,
+        neg_pos_ub=512,
+        neg_balance_thr=0,
+        min_pos_iou=0.5,
+        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, max_per_img=100, nms_thr=0.5, 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/rpn_r50_fpn_1x.py

+# model settings
+model = dict(
+    type='RPN',
+    pretrained='modelzoo://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        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(
+        pos_fraction=0.5,
+        pos_balance_sampling=False,
+        neg_pos_ub=256,
+        allowed_border=0,
+        crowd_thr=1.1,
+        anchor_batch_size=256,
+        pos_iou_thr=0.7,
+        neg_iou_thr=0.3,
+        neg_balance_thr=0,
+        min_pos_iou=0.3,
+        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_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

mmdet/__init__.py

+from .version import __version__, short_version
+
+__all__ = ['__version__', 'short_version']

mmdet/apis/__init__.py

+from .env import init_dist, get_root_logger, set_random_seed
+from .train import train_detector
+from .inference import inference_detector, show_result
+
+__all__ = [
+    'init_dist', 'get_root_logger', 'set_random_seed', 'train_detector',
+    'inference_detector', 'show_result'
+]

mmdet/apis/env.py

+import logging
+import os
+import random
+
+import numpy as np
+import torch
+import torch.distributed as dist
+import torch.multiprocessing as mp
+from mmcv.runner import get_dist_info
+
+
+def init_dist(launcher, backend='nccl', **kwargs):
+    if mp.get_start_method(allow_none=True) is None:
+        mp.set_start_method('spawn')
+    if launcher == 'pytorch':
+        _init_dist_pytorch(backend, **kwargs)
+    elif launcher == 'mpi':
+        _init_dist_mpi(backend, **kwargs)
+    elif launcher == 'slurm':
+        _init_dist_slurm(backend, **kwargs)
+    else:
+        raise ValueError('Invalid launcher type: {}'.format(launcher))
+
+
+def _init_dist_pytorch(backend, **kwargs):
+    # TODO: use local_rank instead of rank % num_gpus
+    rank = int(os.environ['RANK'])
+    num_gpus = torch.cuda.device_count()
+    torch.cuda.set_device(rank % num_gpus)
+    dist.init_process_group(backend=backend, **kwargs)
+
+
+def _init_dist_mpi(backend, **kwargs):
+    raise NotImplementedError
+
+
+def _init_dist_slurm(backend, **kwargs):
+    raise NotImplementedError
+
+
+def set_random_seed(seed):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+
+
+def get_root_logger(log_level=logging.INFO):
+    logger = logging.getLogger()
+    if not logger.hasHandlers():
+        logging.basicConfig(
+            format='%(asctime)s - %(levelname)s - %(message)s',
+            level=log_level)
+    rank, _ = get_dist_info()
+    if rank != 0:
+        logger.setLevel('ERROR')
+    return logger

mmdet/apis/inference.py

+import mmcv
+import numpy as np
+import torch
+
+from mmdet.datasets import to_tensor
+from mmdet.datasets.transforms import ImageTransform
+from mmdet.core import get_classes
+
+
+def _prepare_data(img, img_transform, cfg, device):
+    ori_shape = img.shape
+    img, img_shape, pad_shape, scale_factor = img_transform(
+        img, scale=cfg.data.test.img_scale)
+    img = to_tensor(img).to(device).unsqueeze(0)
+    img_meta = [
+        dict(
+            ori_shape=ori_shape,
+            img_shape=img_shape,
+            pad_shape=pad_shape,
+            scale_factor=scale_factor,
+            flip=False)
+    ]
+    return dict(img=[img], img_meta=[img_meta])
+
+
+def _inference_single(model, img, img_transform, cfg, device):
+    img = mmcv.imread(img)
+    data = _prepare_data(img, img_transform, cfg, device)
+    with torch.no_grad():
+        result = model(return_loss=False, rescale=True, **data)
+    return result
+
+
+def _inference_generator(model, imgs, img_transform, cfg, device):
+    for img in imgs:
+        yield _inference_single(model, img, img_transform, cfg, device)
+
+
+def inference_detector(model, imgs, cfg, device='cuda:0'):
+    img_transform = ImageTransform(
+        size_divisor=cfg.data.test.size_divisor, **cfg.img_norm_cfg)
+    model = model.to(device)
+    model.eval()
+
+    if not isinstance(imgs, list):
+        return _inference_single(model, imgs, img_transform, cfg, device)
+    else:
+        return _inference_generator(model, imgs, img_transform, cfg, device)
+
+
+def show_result(img, result, dataset='coco', score_thr=0.3):
+    class_names = get_classes(dataset)
+    labels = [
+        np.full(bbox.shape[0], i, dtype=np.int32)
+        for i, bbox in enumerate(result)
+    ]
+    labels = np.concatenate(labels)
+    bboxes = np.vstack(result)
+    img = mmcv.imread(img)
+    mmcv.imshow_det_bboxes(
+        img.copy(),
+        bboxes,
+        labels,
+        class_names=class_names,
+        score_thr=score_thr)

mmdet/apis/train.py

+from __future__ import division
+
+from collections import OrderedDict
+
+import torch
+from mmcv.runner import Runner, DistSamplerSeedHook
+from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
+
+from mmdet.core import (DistOptimizerHook, CocoDistEvalRecallHook,
+                        CocoDistEvalmAPHook)
+from mmdet.datasets import build_dataloader
+from mmdet.models import RPN
+from .env import get_root_logger
+
+
+def parse_losses(losses):
+    log_vars = OrderedDict()
+    for loss_name, loss_value in losses.items():
+        if isinstance(loss_value, torch.Tensor):
+            log_vars[loss_name] = loss_value.mean()
+        elif isinstance(loss_value, list):
+            log_vars[loss_name] = sum(_loss.mean() for _loss in loss_value)
+        else:
+            raise TypeError(
+                '{} is not a tensor or list of tensors'.format(loss_name))
+
+    loss = sum(_value for _key, _value in log_vars.items() if 'loss' in _key)
+
+    log_vars['loss'] = loss
+    for name in log_vars:
+        log_vars[name] = log_vars[name].item()
+
+    return loss, log_vars
+
+
+def batch_processor(model, data, train_mode):
+    losses = model(**data)
+    loss, log_vars = parse_losses(losses)
+
+    outputs = dict(
+        loss=loss, log_vars=log_vars, num_samples=len(data['img'].data))
+
+    return outputs
+
+
+def train_detector(model,
+                   dataset,
+                   cfg,
+                   distributed=False,
+                   validate=False,
+                   logger=None):
+    if logger is None:
+        logger = get_root_logger(cfg.log_level)
+
+    # start training
+    if distributed:
+        _dist_train(model, dataset, cfg, validate=validate)
+    else:
+        _non_dist_train(model, dataset, cfg, validate=validate)
+
+
+def _dist_train(model, dataset, cfg, validate=False):
+    # prepare data loaders
+    data_loaders = [
+        build_dataloader(
+            dataset,
+            cfg.data.imgs_per_gpu,
+            cfg.data.workers_per_gpu,
+            dist=True)
+    ]
+    # put model on gpus
+    model = MMDistributedDataParallel(model.cuda())
+    # build runner
+    runner = Runner(model, batch_processor, cfg.optimizer, cfg.work_dir,
+                    cfg.log_level)
+    # register hooks
+    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
+    runner.register_training_hooks(cfg.lr_config, optimizer_config,
+                                   cfg.checkpoint_config, cfg.log_config)
+    runner.register_hook(DistSamplerSeedHook())
+    # register eval hooks
+    if validate:
+        if isinstance(model.module, RPN):
+            runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
+        elif cfg.data.val.type == 'CocoDataset':
+            runner.register_hook(CocoDistEvalmAPHook(cfg.data.val))
+
+    if cfg.resume_from:
+        runner.resume(cfg.resume_from)
+    elif cfg.load_from:
+        runner.load_checkpoint(cfg.load_from)
+    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
+
+
+def _non_dist_train(model, dataset, cfg, validate=False):
+    # prepare data loaders
+    data_loaders = [
+        build_dataloader(
+            dataset,
+            cfg.data.imgs_per_gpu,
+            cfg.data.workers_per_gpu,
+            cfg.gpus,
+            dist=False)
+    ]
+    # put model on gpus
+    model = MMDataParallel(model, device_ids=range(cfg.gpus)).cuda()
+    # build runner
+    runner = Runner(model, batch_processor, cfg.optimizer, cfg.work_dir,
+                    cfg.log_level)
+    runner.register_training_hooks(cfg.lr_config, cfg.optimizer_config,
+                                   cfg.checkpoint_config, cfg.log_config)
+
+    if cfg.resume_from:
+        runner.resume(cfg.resume_from)
+    elif cfg.load_from:
+        runner.load_checkpoint(cfg.load_from)
+    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)

mmdet/core/__init__.py

+from .anchor import *  # noqa: F401, F403
+from .bbox import *  # noqa: F401, F403
+from .mask import *  # noqa: F401, F403
+from .loss import *  # noqa: F401, F403
+from .evaluation import *  # noqa: F401, F403
+from .post_processing import *  # noqa: F401, F403
+from .utils import *  # noqa: F401, F403

mmdet/core/anchor/__init__.py

+from .anchor_generator import AnchorGenerator
+from .anchor_target import anchor_target
+
+__all__ = ['AnchorGenerator', 'anchor_target']

mmdet/core/anchor/anchor_generator.py

+import torch
+
+
+class AnchorGenerator(object):
+
+    def __init__(self, base_size, scales, ratios, scale_major=True):
+        self.base_size = base_size
+        self.scales = torch.Tensor(scales)
+        self.ratios = torch.Tensor(ratios)
+        self.scale_major = scale_major
+        self.base_anchors = self.gen_base_anchors()
+
+    @property
+    def num_base_anchors(self):
+        return self.base_anchors.size(0)
+
+    def gen_base_anchors(self):
+        base_anchor = torch.Tensor(
+            [0, 0, self.base_size - 1, self.base_size - 1])
+
+        w = base_anchor[2] - base_anchor[0] + 1
+        h = base_anchor[3] - base_anchor[1] + 1
+        x_ctr = base_anchor[0] + 0.5 * (w - 1)
+        y_ctr = base_anchor[1] + 0.5 * (h - 1)
+
+        h_ratios = torch.sqrt(self.ratios)
+        w_ratios = 1 / h_ratios
+        if self.scale_major:
+            ws = (w * w_ratios[:, None] * self.scales[None, :]).view(-1)
+            hs = (h * h_ratios[:, None] * self.scales[None, :]).view(-1)
+        else:
+            ws = (w * self.scales[:, None] * w_ratios[None, :]).view(-1)
+            hs = (h * self.scales[:, None] * h_ratios[None, :]).view(-1)
+
+        base_anchors = torch.stack(
+            [
+                x_ctr - 0.5 * (ws - 1), y_ctr - 0.5 * (hs - 1),
+                x_ctr + 0.5 * (ws - 1), y_ctr + 0.5 * (hs - 1)
+            ],
+            dim=-1).round()
+
+        return base_anchors
+
+    def _meshgrid(self, x, y, row_major=True):
+        xx = x.repeat(len(y))
+        yy = y.view(-1, 1).repeat(1, len(x)).view(-1)
+        if row_major:
+            return xx, yy
+        else:
+            return yy, xx
+
+    def grid_anchors(self, featmap_size, stride=16, device='cuda'):
+        base_anchors = self.base_anchors.to(device)
+
+        feat_h, feat_w = featmap_size
+        shift_x = torch.arange(0, feat_w, device=device) * stride
+        shift_y = torch.arange(0, feat_h, device=device) * stride
+        shift_xx, shift_yy = self._meshgrid(shift_x, shift_y)
+        shifts = torch.stack([shift_xx, shift_yy, shift_xx, shift_yy], dim=-1)
+        shifts = shifts.type_as(base_anchors)
+        # first feat_w elements correspond to the first row of shifts
+        # add A anchors (1, A, 4) to K shifts (K, 1, 4) to get
+        # shifted anchors (K, A, 4), reshape to (K*A, 4)
+
+        all_anchors = base_anchors[None, :, :] + shifts[:, None, :]
+        all_anchors = all_anchors.view(-1, 4)
+        # first A rows correspond to A anchors of (0, 0) in feature map,
+        # then (0, 1), (0, 2), ...
+        return all_anchors
+
+    def valid_flags(self, featmap_size, valid_size, device='cuda'):
+        feat_h, feat_w = featmap_size
+        valid_h, valid_w = valid_size
+        assert valid_h <= feat_h and valid_w <= feat_w
+        valid_x = torch.zeros(feat_w, dtype=torch.uint8, device=device)
+        valid_y = torch.zeros(feat_h, dtype=torch.uint8, device=device)
+        valid_x[:valid_w] = 1
+        valid_y[:valid_h] = 1
+        valid_xx, valid_yy = self._meshgrid(valid_x, valid_y)
+        valid = valid_xx & valid_yy
+        valid = valid[:, None].expand(
+            valid.size(0), self.num_base_anchors).contiguous().view(-1)
+        return valid

mmdet/core/anchor/anchor_target.py

+import torch
+
+from ..bbox import bbox_assign, bbox2delta, bbox_sampling
+from ..utils import multi_apply
+
+
+def anchor_target(anchor_list, valid_flag_list, gt_bboxes_list, img_metas,
+                  target_means, target_stds, cfg):
+    """Compute regression and classification targets for anchors.
+
+    Args:
+        anchor_list (list[list]): Multi level anchors of each image.
+        valid_flag_list (list[list]): Multi level valid flags of each image.
+        gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
+        img_metas (list[dict]): Meta info of each image.
+        target_means (Iterable): Mean value of regression targets.
+        target_stds (Iterable): Std value of regression targets.
+        cfg (dict): RPN train configs.
+
+    Returns:
+        tuple
+    """
+    num_imgs = len(img_metas)
+    assert len(anchor_list) == len(valid_flag_list) == num_imgs
+
+    # anchor number of multi levels
+    num_level_anchors = [anchors.size(0) for anchors in anchor_list[0]]
+    # concat all level anchors and flags to a single tensor
+    for i in range(num_imgs):
+        assert len(anchor_list[i]) == len(valid_flag_list[i])
+        anchor_list[i] = torch.cat(anchor_list[i])
+        valid_flag_list[i] = torch.cat(valid_flag_list[i])
+
+    # compute targets for each image
+    means_replicas = [target_means for _ in range(num_imgs)]
+    stds_replicas = [target_stds for _ in range(num_imgs)]
+    cfg_replicas = [cfg for _ in range(num_imgs)]
+    (all_labels, all_label_weights, all_bbox_targets,
+     all_bbox_weights, pos_inds_list, neg_inds_list) = multi_apply(
+         anchor_target_single, anchor_list, valid_flag_list, gt_bboxes_list,
+         img_metas, means_replicas, stds_replicas, cfg_replicas)
+    # no valid anchors
+    if any([labels is None for labels in all_labels]):
+        return None
+    # sampled anchors of all images
+    num_total_samples = sum([
+        max(pos_inds.numel() + neg_inds.numel(), 1)
+        for pos_inds, neg_inds in zip(pos_inds_list, neg_inds_list)
+    ])
+    # split targets to a list w.r.t. multiple levels
+    labels_list = images_to_levels(all_labels, num_level_anchors)
+    label_weights_list = images_to_levels(all_label_weights, num_level_anchors)
+    bbox_targets_list = images_to_levels(all_bbox_targets, num_level_anchors)
+    bbox_weights_list = images_to_levels(all_bbox_weights, num_level_anchors)
+    return (labels_list, label_weights_list, bbox_targets_list,
+            bbox_weights_list, num_total_samples)
+
+
+def images_to_levels(target, num_level_anchors):
+    """Convert targets by image to targets by feature level.
+
+    [target_img0, target_img1] -> [target_level0, target_level1, ...]
+    """
+    target = torch.stack(target, 0)
+    level_targets = []
+    start = 0
+    for n in num_level_anchors:
+        end = start + n
+        level_targets.append(target[:, start:end].squeeze(0))
+        start = end
+    return level_targets
+
+
+def anchor_target_single(flat_anchors, valid_flags, gt_bboxes, img_meta,
+                         target_means, target_stds, cfg):
+    inside_flags = anchor_inside_flags(flat_anchors, valid_flags,
+                                       img_meta['img_shape'][:2],
+                                       cfg.allowed_border)
+    if not inside_flags.any():
+        return (None, ) * 6
+    # assign gt and sample anchors
+    anchors = flat_anchors[inside_flags, :]
+    assigned_gt_inds, argmax_overlaps, max_overlaps = bbox_assign(
+        anchors,
+        gt_bboxes,
+        pos_iou_thr=cfg.pos_iou_thr,
+        neg_iou_thr=cfg.neg_iou_thr,
+        min_pos_iou=cfg.min_pos_iou)
+    pos_inds, neg_inds = bbox_sampling(assigned_gt_inds, cfg.anchor_batch_size,
+                                       cfg.pos_fraction, cfg.neg_pos_ub,
+                                       cfg.pos_balance_sampling, max_overlaps,
+                                       cfg.neg_balance_thr)
+
+    bbox_targets = torch.zeros_like(anchors)
+    bbox_weights = torch.zeros_like(anchors)
+    labels = torch.zeros_like(assigned_gt_inds)
+    label_weights = torch.zeros_like(assigned_gt_inds, dtype=anchors.dtype)
+
+    if len(pos_inds) > 0:
+        pos_anchors = anchors[pos_inds, :]
+        pos_gt_bbox = gt_bboxes[assigned_gt_inds[pos_inds] - 1, :]
+        pos_bbox_targets = bbox2delta(pos_anchors, pos_gt_bbox, target_means,
+                                      target_stds)
+        bbox_targets[pos_inds, :] = pos_bbox_targets
+        bbox_weights[pos_inds, :] = 1.0
+        labels[pos_inds] = 1
+        if cfg.pos_weight <= 0:
+            label_weights[pos_inds] = 1.0
+        else:
+            label_weights[pos_inds] = cfg.pos_weight
+    if len(neg_inds) > 0:
+        label_weights[neg_inds] = 1.0
+
+    # map up to original set of anchors
+    num_total_anchors = flat_anchors.size(0)
+    labels = unmap(labels, num_total_anchors, inside_flags)
+    label_weights = unmap(label_weights, num_total_anchors, inside_flags)
+    bbox_targets = unmap(bbox_targets, num_total_anchors, inside_flags)
+    bbox_weights = unmap(bbox_weights, num_total_anchors, inside_flags)
+
+    return (labels, label_weights, bbox_targets, bbox_weights, pos_inds,
+            neg_inds)
+
+
+def anchor_inside_flags(flat_anchors, valid_flags, img_shape,
+                        allowed_border=0):
+    img_h, img_w = img_shape[:2]
+    if allowed_border >= 0:
+        inside_flags = valid_flags & \
+            (flat_anchors[:, 0] >= -allowed_border) & \
+            (flat_anchors[:, 1] >= -allowed_border) & \
+            (flat_anchors[:, 2] < img_w + allowed_border) & \
+            (flat_anchors[:, 3] < img_h + allowed_border)
+    else:
+        inside_flags = valid_flags
+    return inside_flags
+
+
+def unmap(data, count, inds, fill=0):
+    """ Unmap a subset of item (data) back to the original set of items (of
+    size count) """
+    if data.dim() == 1:
+        ret = data.new_full((count, ), fill)
+        ret[inds] = data
+    else:
+        new_size = (count, ) + data.size()[1:]
+        ret = data.new_full(new_size, fill)
+        ret[inds, :] = data
+    return ret

mmdet/core/bbox/__init__.py

+from .geometry import bbox_overlaps
+from .sampling import (random_choice, bbox_assign, bbox_assign_wrt_overlaps,
+                       bbox_sampling, bbox_sampling_pos, bbox_sampling_neg,
+                       sample_bboxes)
+from .transforms import (bbox2delta, delta2bbox, bbox_flip, bbox_mapping,
+                         bbox_mapping_back, bbox2roi, roi2bbox, bbox2result)
+from .bbox_target import bbox_target
+
+__all__ = [
+    'bbox_overlaps', 'random_choice', 'bbox_assign',
+    'bbox_assign_wrt_overlaps', 'bbox_sampling', 'bbox_sampling_pos',
+    'bbox_sampling_neg', 'sample_bboxes', 'bbox2delta', 'delta2bbox',
+    'bbox_flip', 'bbox_mapping', 'bbox_mapping_back', 'bbox2roi', 'roi2bbox',
+    'bbox2result', 'bbox_target'
+]

mmdet/core/bbox/bbox_target.py

+import torch
+
+from .transforms import bbox2delta
+from ..utils import multi_apply
+
+
+def bbox_target(pos_proposals_list,
+                neg_proposals_list,
+                pos_gt_bboxes_list,
+                pos_gt_labels_list,
+                cfg,
+                reg_num_classes=1,
+                target_means=[.0, .0, .0, .0],
+                target_stds=[1.0, 1.0, 1.0, 1.0],
+                concat=True):
+    labels, label_weights, bbox_targets, bbox_weights = multi_apply(
+        proposal_target_single,
+        pos_proposals_list,
+        neg_proposals_list,
+        pos_gt_bboxes_list,
+        pos_gt_labels_list,
+        cfg=cfg,
+        reg_num_classes=reg_num_classes,
+        target_means=target_means,
+        target_stds=target_stds)
+
+    if concat:
+        labels = torch.cat(labels, 0)
+        label_weights = torch.cat(label_weights, 0)
+        bbox_targets = torch.cat(bbox_targets, 0)
+        bbox_weights = torch.cat(bbox_weights, 0)
+    return labels, label_weights, bbox_targets, bbox_weights
+
+
+def proposal_target_single(pos_proposals,
+                           neg_proposals,
+                           pos_gt_bboxes,
+                           pos_gt_labels,
+                           cfg,
+                           reg_num_classes=1,
+                           target_means=[.0, .0, .0, .0],
+                           target_stds=[1.0, 1.0, 1.0, 1.0]):
+    num_pos = pos_proposals.size(0)
+    num_neg = neg_proposals.size(0)
+    num_samples = num_pos + num_neg
+    labels = pos_proposals.new_zeros(num_samples, dtype=torch.long)
+    label_weights = pos_proposals.new_zeros(num_samples)
+    bbox_targets = pos_proposals.new_zeros(num_samples, 4)
+    bbox_weights = pos_proposals.new_zeros(num_samples, 4)
+    if num_pos > 0:
+        labels[:num_pos] = pos_gt_labels
+        pos_weight = 1.0 if cfg.pos_weight <= 0 else cfg.pos_weight
+        label_weights[:num_pos] = pos_weight
+        pos_bbox_targets = bbox2delta(pos_proposals, pos_gt_bboxes,
+                                      target_means, target_stds)
+        bbox_targets[:num_pos, :] = pos_bbox_targets
+        bbox_weights[:num_pos, :] = 1
+    if num_neg > 0:
+        label_weights[-num_neg:] = 1.0
+    if reg_num_classes > 1:
+        bbox_targets, bbox_weights = expand_target(bbox_targets, bbox_weights,
+                                                   labels, reg_num_classes)
+
+    return labels, label_weights, bbox_targets, bbox_weights
+
+
+def expand_target(bbox_targets, bbox_weights, labels, num_classes):
+    bbox_targets_expand = bbox_targets.new_zeros((bbox_targets.size(0),
+                                                  4 * num_classes))
+    bbox_weights_expand = bbox_weights.new_zeros((bbox_weights.size(0),
+                                                  4 * num_classes))
+    for i in torch.nonzero(labels > 0).squeeze(-1):
+        start, end = labels[i] * 4, (labels[i] + 1) * 4
+        bbox_targets_expand[i, start:end] = bbox_targets[i, :]
+        bbox_weights_expand[i, start:end] = bbox_weights[i, :]
+    return bbox_targets_expand, bbox_weights_expand

mmdet/core/bbox/geometry.py

+import torch
+
+
+def bbox_overlaps(bboxes1, bboxes2, mode='iou', is_aligned=False):
+    """Calculate overlap between two set of bboxes.
+
+    If ``is_aligned`` is ``False``, then calculate the ious between each bbox
+    of bboxes1 and bboxes2, otherwise the ious between each aligned pair of
+    bboxes1 and bboxes2.
+
+    Args:
+        bboxes1 (Tensor): shape (m, 4)
+        bboxes2 (Tensor): shape (n, 4), if is_aligned is ``True``, then m and n
+            must be equal.
+        mode (str): "iou" (intersection over union) or iof (intersection over
+            foreground).
+
+    Returns:
+        ious(Tensor): shape (n, k) if is_aligned == False else shape (n, 1)
+    """
+
+    assert mode in ['iou', 'iof']
+
+    rows = bboxes1.size(0)
+    cols = bboxes2.size(0)
+    if is_aligned:
+        assert rows == cols
+
+    if rows * cols == 0:
+        return bboxes1.new(rows, 1) if is_aligned else bboxes1.new(rows, cols)
+
+    if is_aligned:
+        lt = torch.max(bboxes1[:, :2], bboxes2[:, :2])  # [rows, 2]
+        rb = torch.min(bboxes1[:, 2:], bboxes2[:, 2:])  # [rows, 2]
+
+        wh = (rb - lt + 1).clamp(min=0)  # [rows, 2]
+        overlap = wh[:, 0] * wh[:, 1]
+        area1 = (bboxes1[:, 2] - bboxes1[:, 0] + 1) * (
+            bboxes1[:, 3] - bboxes1[:, 1] + 1)
+
+        if mode == 'iou':
+            area2 = (bboxes2[:, 2] - bboxes2[:, 0] + 1) * (
+                bboxes2[:, 3] - bboxes2[:, 1] + 1)
+            ious = overlap / (area1 + area2 - overlap)
+        else:
+            ious = overlap / area1
+    else:
+        lt = torch.max(bboxes1[:, None, :2], bboxes2[:, :2])  # [rows, cols, 2]
+        rb = torch.min(bboxes1[:, None, 2:], bboxes2[:, 2:])  # [rows, cols, 2]
+
+        wh = (rb - lt + 1).clamp(min=0)  # [rows, cols, 2]
+        overlap = wh[:, :, 0] * wh[:, :, 1]
+        area1 = (bboxes1[:, 2] - bboxes1[:, 0] + 1) * (
+            bboxes1[:, 3] - bboxes1[:, 1] + 1)
+
+        if mode == 'iou':
+            area2 = (bboxes2[:, 2] - bboxes2[:, 0] + 1) * (
+                bboxes2[:, 3] - bboxes2[:, 1] + 1)
+            ious = overlap / (area1[:, None] + area2 - overlap)
+        else:
+            ious = overlap / (area1[:, None])
+
+    return ious