update codes

mmdet/configs/panoptic_fpn/panoptic_fpn_r50_fpn_ms_3x_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from mmengine.config import read_base
+from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
+
+with read_base():
+    from .panoptic_fpn_r50_fpn_1x_coco import *
+
+from mmcv.transforms import RandomResize
+from mmcv.transforms.loading import LoadImageFromFile
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadPanopticAnnotations
+from mmdet.datasets.transforms.transforms import RandomFlip
+
+# In mstrain 3x config, img_scale=[(1333, 640), (1333, 800)],
+# multiscale_mode='range'
+train_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=LoadPanopticAnnotations,
+        with_bbox=True,
+        with_mask=True,
+        with_seg=True),
+    dict(type=RandomResize, scale=[(1333, 640), (1333, 800)], keep_ratio=True),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))
+
+# TODO: Use RepeatDataset to speed up training
+# training schedule for 3x
+train_cfg.update(dict(max_epochs=36, val_interval=3))
+
+# learning rate
+param_scheduler = [
+    dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type=MultiStepLR,
+        begin=0,
+        end=36,
+        by_epoch=True,
+        milestones=[24, 33],
+        gamma=0.1)
+]

mmdet/configs/qdtrack/qdtrack_faster_rcnn_r50_fpn_4e_base.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from mmengine.config import read_base
+
+with read_base():
+    from .._base_.models.faster_rcnn_r50_fpn import *
+    from .._base_.models.faster_rcnn_r50_fpn import model
+    from .._base_.default_runtime import *
+
+from mmcv.ops import RoIAlign
+from mmengine.hooks import LoggerHook, SyncBuffersHook
+from mmengine.model.weight_init import PretrainedInit
+from mmengine.optim import MultiStepLR, OptimWrapper
+from mmengine.runner.runner import EpochBasedTrainLoop, TestLoop, ValLoop
+from torch.nn.modules.batchnorm import BatchNorm2d
+from torch.nn.modules.normalization import GroupNorm
+from torch.optim import SGD
+
+from mmdet.engine.hooks import TrackVisualizationHook
+from mmdet.models import (QDTrack, QuasiDenseEmbedHead, QuasiDenseTracker,
+                          QuasiDenseTrackHead, SingleRoIExtractor,
+                          TrackDataPreprocessor)
+from mmdet.models.losses import (L1Loss, MarginL2Loss,
+                                 MultiPosCrossEntropyLoss, SmoothL1Loss)
+from mmdet.models.task_modules import (CombinedSampler,
+                                       InstanceBalancedPosSampler,
+                                       MaxIoUAssigner, RandomSampler)
+from mmdet.visualization import TrackLocalVisualizer
+
+detector = model
+detector.pop('data_preprocessor')
+
+detector['backbone'].update(
+    dict(
+        norm_cfg=dict(type=BatchNorm2d, requires_grad=False),
+        style='caffe',
+        init_cfg=dict(
+            type=PretrainedInit,
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')))
+detector.rpn_head.loss_bbox.update(
+    dict(type=SmoothL1Loss, beta=1.0 / 9.0, loss_weight=1.0))
+detector.rpn_head.bbox_coder.update(dict(clip_border=False))
+detector.roi_head.bbox_head.update(dict(num_classes=1))
+detector.roi_head.bbox_head.bbox_coder.update(dict(clip_border=False))
+detector['init_cfg'] = dict(
+    type=PretrainedInit,
+    checkpoint=  # noqa: E251
+    'https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/'
+    'faster_rcnn_r50_fpn_1x_coco-person/'
+    'faster_rcnn_r50_fpn_1x_coco-person_20201216_175929-d022e227.pth'
+    # noqa: E501
+)
+del model
+
+model = dict(
+    type=QDTrack,
+    data_preprocessor=dict(
+        type=TrackDataPreprocessor,
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    detector=detector,
+    track_head=dict(
+        type=QuasiDenseTrackHead,
+        roi_extractor=dict(
+            type=SingleRoIExtractor,
+            roi_layer=dict(type=RoIAlign, output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        embed_head=dict(
+            type=QuasiDenseEmbedHead,
+            num_convs=4,
+            num_fcs=1,
+            embed_channels=256,
+            norm_cfg=dict(type=GroupNorm, num_groups=32),
+            loss_track=dict(type=MultiPosCrossEntropyLoss, loss_weight=0.25),
+            loss_track_aux=dict(
+                type=MarginL2Loss,
+                neg_pos_ub=3,
+                pos_margin=0,
+                neg_margin=0.1,
+                hard_mining=True,
+                loss_weight=1.0)),
+        loss_bbox=dict(type=L1Loss, loss_weight=1.0),
+        train_cfg=dict(
+            assigner=dict(
+                type=MaxIoUAssigner,
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type=CombinedSampler,
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=3,
+                add_gt_as_proposals=True,
+                pos_sampler=dict(type=InstanceBalancedPosSampler),
+                neg_sampler=dict(type=RandomSampler)))),
+    tracker=dict(
+        type=QuasiDenseTracker,
+        init_score_thr=0.9,
+        obj_score_thr=0.5,
+        match_score_thr=0.5,
+        memo_tracklet_frames=30,
+        memo_backdrop_frames=1,
+        memo_momentum=0.8,
+        nms_conf_thr=0.5,
+        nms_backdrop_iou_thr=0.3,
+        nms_class_iou_thr=0.7,
+        with_cats=True,
+        match_metric='bisoftmax'))
+# optimizer
+optim_wrapper = dict(
+    type=OptimWrapper,
+    optimizer=dict(type=SGD, lr=0.02, momentum=0.9, weight_decay=0.0001),
+    clip_grad=dict(max_norm=35, norm_type=2))
+# learning policy
+param_scheduler = [
+    dict(type=MultiStepLR, begin=0, end=4, by_epoch=True, milestones=[3])
+]
+
+# runtime settings
+train_cfg = dict(type=EpochBasedTrainLoop, max_epochs=4, val_interval=4)
+val_cfg = dict(type=ValLoop)
+test_cfg = dict(type=TestLoop)
+
+default_hooks.update(
+    logger=dict(type=LoggerHook, interval=50),
+    visualization=dict(type=TrackVisualizationHook, draw=False))
+
+visualizer.update(
+    type=TrackLocalVisualizer, vis_backends=vis_backends, name='visualizer')
+
+# custom hooks
+custom_hooks = [
+    # Synchronize model buffers such as running_mean and running_var in BN
+    # at the end of each epoch
+    dict(type=SyncBuffersHook)
+]

mmdet/configs/qdtrack/qdtrack_faster_rcnn_r50_fpn_8xb2-4e_mot17halftrain_test-mot17halfval.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from mmengine.config import read_base
+
+with read_base():
+    from .._base_.datasets.mot_challenge import *
+    from .qdtrack_faster_rcnn_r50_fpn_4e_base import *
+
+from mmdet.evaluation import CocoVideoMetric, MOTChallengeMetric
+
+# evaluator
+val_evaluator = [
+    dict(type=CocoVideoMetric, metric=['bbox'], classwise=True),
+    dict(type=MOTChallengeMetric, metric=['HOTA', 'CLEAR', 'Identity'])
+]

mmdet/configs/retinanet/retinanet_r50_fpn_1x_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .._base_.models.retinanet_r50_fpn import *
+    from .._base_.datasets.coco_detection import *
+    from .._base_.schedules.schedule_1x import *
+    from .._base_.default_runtime import *
+    from .retinanet_tta import *
+
+from torch.optim.sgd import SGD
+
+# optimizer
+optim_wrapper.update(
+    dict(optimizer=dict(type=SGD, lr=0.01, momentum=0.9, weight_decay=0.0001)))

mmdet/configs/retinanet/retinanet_tta.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import TestTimeAug
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadAnnotations
+from mmdet.datasets.transforms.transforms import RandomFlip, Resize
+from mmdet.models.test_time_augs.det_tta import DetTTAModel
+
+tta_model = dict(
+    type=DetTTAModel,
+    tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.5), max_per_img=100))
+
+img_scales = [(1333, 800), (666, 400), (2000, 1200)]
+tta_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=None),
+    dict(
+        type=TestTimeAug,
+        transforms=[
+            [dict(type=Resize, scale=s, keep_ratio=True) for s in img_scales],
+            [dict(type=RandomFlip, prob=1.),
+             dict(type=RandomFlip, prob=0.)],
+            [dict(type=LoadAnnotations, with_bbox=True)],
+            [
+                dict(
+                    type=PackDetInputs,
+                    meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                               'scale_factor', 'flip', 'flip_direction'))
+            ]
+        ])
+]

mmdet/configs/rtmdet/rtmdet_ins_l_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_l_8xb32_300e_coco import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+from mmengine.hooks.ema_hook import EMAHook
+from torch.nn.modules.activation import SiLU
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import (FilterAnnotations,
+                                               LoadAnnotations)
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+from mmdet.engine.hooks.pipeline_switch_hook import PipelineSwitchHook
+from mmdet.models.dense_heads.rtmdet_ins_head import RTMDetInsSepBNHead
+from mmdet.models.layers.ema import ExpMomentumEMA
+from mmdet.models.losses.dice_loss import DiceLoss
+from mmdet.models.losses.gfocal_loss import QualityFocalLoss
+from mmdet.models.losses.iou_loss import GIoULoss
+from mmdet.models.task_modules.coders.distance_point_bbox_coder import \
+    DistancePointBBoxCoder
+from mmdet.models.task_modules.prior_generators.point_generator import \
+    MlvlPointGenerator
+
+model.merge(
+    dict(
+        bbox_head=dict(
+            _delete_=True,
+            type=RTMDetInsSepBNHead,
+            num_classes=80,
+            in_channels=256,
+            stacked_convs=2,
+            share_conv=True,
+            pred_kernel_size=1,
+            feat_channels=256,
+            act_cfg=dict(type=SiLU, inplace=True),
+            norm_cfg=dict(type='SyncBN', requires_grad=True),
+            anchor_generator=dict(
+                type=MlvlPointGenerator, offset=0, strides=[8, 16, 32]),
+            bbox_coder=dict(type=DistancePointBBoxCoder),
+            loss_cls=dict(
+                type=QualityFocalLoss,
+                use_sigmoid=True,
+                beta=2.0,
+                loss_weight=1.0),
+            loss_bbox=dict(type=GIoULoss, loss_weight=2.0),
+            loss_mask=dict(
+                type=DiceLoss, loss_weight=2.0, eps=5e-6, reduction='mean')),
+        test_cfg=dict(
+            nms_pre=1000,
+            min_bbox_size=0,
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.6),
+            max_per_img=100,
+            mask_thr_binary=0.5),
+    ))
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(type=CachedMosaic, img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.1, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(
+        type=RandomCrop,
+        crop_size=(640, 640),
+        recompute_bbox=True,
+        allow_negative_crop=True),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(
+    dict(pin_memory=True, dataset=dict(pipeline=train_pipeline)))
+
+train_pipeline_stage2 = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(
+        type=RandomResize,
+        scale=(640, 640),
+        ratio_range=(0.1, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(
+        type=RandomCrop,
+        crop_size=(640, 640),
+        recompute_bbox=True,
+        allow_negative_crop=True),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type=PackDetInputs)
+]
+custom_hooks = [
+    dict(
+        type=EMAHook,
+        ema_type=ExpMomentumEMA,
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type=PipelineSwitchHook,
+        switch_epoch=280,
+        switch_pipeline=train_pipeline_stage2)
+]
+
+val_evaluator.update(dict(metric=['bbox', 'segm']))
+test_evaluator = val_evaluator

mmdet/configs/rtmdet/rtmdet_ins_m_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_ins_l_8xb32_300e_coco import *
+
+model.update(
+    dict(
+        backbone=dict(deepen_factor=0.67, widen_factor=0.75),
+        neck=dict(
+            in_channels=[192, 384, 768], out_channels=192, num_csp_blocks=2),
+        bbox_head=dict(in_channels=192, feat_channels=192)))

mmdet/configs/rtmdet/rtmdet_ins_s_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_ins_l_8xb32_300e_coco import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+from mmengine.hooks.ema_hook import EMAHook
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import (FilterAnnotations,
+                                               LoadAnnotations)
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+from mmdet.engine.hooks.pipeline_switch_hook import PipelineSwitchHook
+from mmdet.models.layers.ema import ExpMomentumEMA
+
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth'  # noqa
+model.update(
+    dict(
+        backbone=dict(
+            deepen_factor=0.33,
+            widen_factor=0.5,
+            init_cfg=dict(
+                type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+        neck=dict(
+            in_channels=[128, 256, 512], out_channels=128, num_csp_blocks=1),
+        bbox_head=dict(in_channels=128, feat_channels=128)))
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(type=CachedMosaic, img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(
+        type=RandomCrop,
+        crop_size=(640, 640),
+        recompute_bbox=True,
+        allow_negative_crop=True),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=PackDetInputs)
+]
+
+train_pipeline_stage2 = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(
+        type=RandomResize,
+        scale=(640, 640),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(
+        type=RandomCrop,
+        crop_size=(640, 640),
+        recompute_bbox=True,
+        allow_negative_crop=True),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))
+
+custom_hooks = [
+    dict(
+        type=EMAHook,
+        ema_type=ExpMomentumEMA,
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type=PipelineSwitchHook,
+        switch_epoch=280,
+        switch_pipeline=train_pipeline_stage2)
+]

mmdet/configs/rtmdet/rtmdet_ins_tiny_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_ins_s_8xb32_300e_coco import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import (FilterAnnotations,
+                                               LoadAnnotations)
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-tiny_imagenet_600e.pth'  # noqa
+
+model.update(
+    dict(
+        backbone=dict(
+            deepen_factor=0.167,
+            widen_factor=0.375,
+            init_cfg=dict(
+                type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+        neck=dict(
+            in_channels=[96, 192, 384], out_channels=96, num_csp_blocks=1),
+        bbox_head=dict(in_channels=96, feat_channels=96)))
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(
+        type=CachedMosaic,
+        img_scale=(640, 640),
+        pad_val=114.0,
+        max_cached_images=20,
+        random_pop=False),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(type=RandomCrop, crop_size=(640, 640)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=10,
+        random_pop=False,
+        pad_val=(114, 114, 114),
+        prob=0.5),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))

mmdet/configs/rtmdet/rtmdet_ins_x_8xb16_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_ins_l_8xb32_300e_coco import *
+from mmengine.optim.scheduler.lr_scheduler import CosineAnnealingLR, LinearLR
+
+model.update(
+    dict(
+        backbone=dict(deepen_factor=1.33, widen_factor=1.25),
+        neck=dict(
+            in_channels=[320, 640, 1280], out_channels=320, num_csp_blocks=4),
+        bbox_head=dict(in_channels=320, feat_channels=320)))
+
+base_lr = 0.002
+
+# optimizer
+optim_wrapper.update(dict(optimizer=dict(lr=base_lr)))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type=LinearLR, start_factor=1.0e-5, by_epoch=False, begin=0, end=1000),
+    dict(
+        # use cosine lr from 150 to 300 epoch
+        type=CosineAnnealingLR,
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]

mmdet/configs/rtmdet/rtmdet_l_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .._base_.default_runtime import *
+    from .._base_.schedules.schedule_1x import *
+    from .._base_.datasets.coco_detection import *
+    from .rtmdet_tta import *
+
+from mmcv.ops import nms
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+from mmengine.hooks.ema_hook import EMAHook
+from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper
+from mmengine.optim.scheduler.lr_scheduler import CosineAnnealingLR, LinearLR
+from torch.nn import SyncBatchNorm
+from torch.nn.modules.activation import SiLU
+from torch.optim.adamw import AdamW
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadAnnotations
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+from mmdet.engine.hooks.pipeline_switch_hook import PipelineSwitchHook
+from mmdet.models.backbones.cspnext import CSPNeXt
+from mmdet.models.data_preprocessors.data_preprocessor import \
+    DetDataPreprocessor
+from mmdet.models.dense_heads.rtmdet_head import RTMDetSepBNHead
+from mmdet.models.detectors.rtmdet import RTMDet
+from mmdet.models.layers.ema import ExpMomentumEMA
+from mmdet.models.losses.gfocal_loss import QualityFocalLoss
+from mmdet.models.losses.iou_loss import GIoULoss
+from mmdet.models.necks.cspnext_pafpn import CSPNeXtPAFPN
+from mmdet.models.task_modules.assigners.dynamic_soft_label_assigner import \
+    DynamicSoftLabelAssigner
+from mmdet.models.task_modules.coders.distance_point_bbox_coder import \
+    DistancePointBBoxCoder
+from mmdet.models.task_modules.prior_generators.point_generator import \
+    MlvlPointGenerator
+
+model = dict(
+    type=RTMDet,
+    data_preprocessor=dict(
+        type=DetDataPreprocessor,
+        mean=[103.53, 116.28, 123.675],
+        std=[57.375, 57.12, 58.395],
+        bgr_to_rgb=False,
+        batch_augments=None),
+    backbone=dict(
+        type=CSPNeXt,
+        arch='P5',
+        expand_ratio=0.5,
+        deepen_factor=1,
+        widen_factor=1,
+        channel_attention=True,
+        norm_cfg=dict(type=SyncBatchNorm),
+        act_cfg=dict(type=SiLU, inplace=True)),
+    neck=dict(
+        type=CSPNeXtPAFPN,
+        in_channels=[256, 512, 1024],
+        out_channels=256,
+        num_csp_blocks=3,
+        expand_ratio=0.5,
+        norm_cfg=dict(type=SyncBatchNorm),
+        act_cfg=dict(type=SiLU, inplace=True)),
+    bbox_head=dict(
+        type=RTMDetSepBNHead,
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=2,
+        feat_channels=256,
+        anchor_generator=dict(
+            type=MlvlPointGenerator, offset=0, strides=[8, 16, 32]),
+        bbox_coder=dict(type=DistancePointBBoxCoder),
+        loss_cls=dict(
+            type=QualityFocalLoss, use_sigmoid=True, beta=2.0,
+            loss_weight=1.0),
+        loss_bbox=dict(type=GIoULoss, loss_weight=2.0),
+        with_objectness=False,
+        exp_on_reg=True,
+        share_conv=True,
+        pred_kernel_size=1,
+        norm_cfg=dict(type=SyncBatchNorm),
+        act_cfg=dict(type=SiLU, inplace=True)),
+    train_cfg=dict(
+        assigner=dict(type=DynamicSoftLabelAssigner, topk=13),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=30000,
+        min_bbox_size=0,
+        score_thr=0.001,
+        nms=dict(type=nms, iou_threshold=0.65),
+        max_per_img=300),
+)
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadAnnotations, with_bbox=True),
+    dict(type=CachedMosaic, img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.1, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(type=RandomCrop, crop_size=(640, 640)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type=PackDetInputs)
+]
+
+train_pipeline_stage2 = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadAnnotations, with_bbox=True),
+    dict(
+        type=RandomResize,
+        scale=(640, 640),
+        ratio_range=(0.1, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(type=RandomCrop, crop_size=(640, 640)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type=PackDetInputs)
+]
+
+test_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=Resize, scale=(640, 640), keep_ratio=True),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type=LoadAnnotations, with_bbox=True),
+    dict(
+        type=PackDetInputs,
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader.update(
+    dict(
+        batch_size=32,
+        num_workers=10,
+        batch_sampler=None,
+        pin_memory=True,
+        dataset=dict(pipeline=train_pipeline)))
+val_dataloader.update(
+    dict(batch_size=5, num_workers=10, dataset=dict(pipeline=test_pipeline)))
+test_dataloader = val_dataloader
+
+max_epochs = 300
+stage2_num_epochs = 20
+base_lr = 0.004
+interval = 10
+
+train_cfg.update(
+    dict(
+        max_epochs=max_epochs,
+        val_interval=interval,
+        dynamic_intervals=[(max_epochs - stage2_num_epochs, 1)]))
+
+val_evaluator.update(dict(proposal_nums=(100, 1, 10)))
+test_evaluator = val_evaluator
+
+# optimizer
+optim_wrapper = dict(
+    type=OptimWrapper,
+    optimizer=dict(type=AdamW, lr=base_lr, weight_decay=0.05),
+    paramwise_cfg=dict(
+        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type=LinearLR, start_factor=1.0e-5, by_epoch=False, begin=0, end=1000),
+    dict(
+        # use cosine lr from 150 to 300 epoch
+        type=CosineAnnealingLR,
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]
+
+# hooks
+default_hooks.update(
+    dict(
+        checkpoint=dict(
+            interval=interval,
+            max_keep_ckpts=3  # only keep latest 3 checkpoints
+        )))
+
+custom_hooks = [
+    dict(
+        type=EMAHook,
+        ema_type=ExpMomentumEMA,
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type=PipelineSwitchHook,
+        switch_epoch=max_epochs - stage2_num_epochs,
+        switch_pipeline=train_pipeline_stage2)
+]

mmdet/configs/rtmdet/rtmdet_m_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_l_8xb32_300e_coco import *
+
+model.update(
+    dict(
+        backbone=dict(deepen_factor=0.67, widen_factor=0.75),
+        neck=dict(
+            in_channels=[192, 384, 768], out_channels=192, num_csp_blocks=2),
+        bbox_head=dict(in_channels=192, feat_channels=192)))

mmdet/configs/rtmdet/rtmdet_s_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_l_8xb32_300e_coco import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+from mmengine.hooks.ema_hook import EMAHook
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadAnnotations
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+from mmdet.engine.hooks.pipeline_switch_hook import PipelineSwitchHook
+from mmdet.models.layers.ema import ExpMomentumEMA
+
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth'  # noqa
+model.update(
+    dict(
+        backbone=dict(
+            deepen_factor=0.33,
+            widen_factor=0.5,
+            init_cfg=dict(
+                type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+        neck=dict(
+            in_channels=[128, 256, 512], out_channels=128, num_csp_blocks=1),
+        bbox_head=dict(in_channels=128, feat_channels=128, exp_on_reg=False)))
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadAnnotations, with_bbox=True),
+    dict(type=CachedMosaic, img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(type=RandomCrop, crop_size=(640, 640)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type=PackDetInputs)
+]
+
+train_pipeline_stage2 = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadAnnotations, with_bbox=True),
+    dict(
+        type=RandomResize,
+        scale=(640, 640),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(type=RandomCrop, crop_size=(640, 640)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))
+
+custom_hooks = [
+    dict(
+        type=EMAHook,
+        ema_type=ExpMomentumEMA,
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type=PipelineSwitchHook,
+        switch_epoch=280,
+        switch_pipeline=train_pipeline_stage2)
+]

mmdet/configs/rtmdet/rtmdet_tiny_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_s_8xb32_300e_coco import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadAnnotations
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-tiny_imagenet_600e.pth'  # noqa
+
+model.update(
+    dict(
+        backbone=dict(
+            deepen_factor=0.167,
+            widen_factor=0.375,
+            init_cfg=dict(
+                type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+        neck=dict(
+            in_channels=[96, 192, 384], out_channels=96, num_csp_blocks=1),
+        bbox_head=dict(in_channels=96, feat_channels=96, exp_on_reg=False)))
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadAnnotations, with_bbox=True),
+    dict(
+        type=CachedMosaic,
+        img_scale=(640, 640),
+        pad_val=114.0,
+        max_cached_images=20,
+        random_pop=False),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(type=RandomCrop, crop_size=(640, 640)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=10,
+        random_pop=False,
+        pad_val=(114, 114, 114),
+        prob=0.5),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))

mmdet/configs/rtmdet/rtmdet_tta.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import TestTimeAug
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadAnnotations
+from mmdet.datasets.transforms.transforms import Pad, RandomFlip, Resize
+from mmdet.models.test_time_augs.det_tta import DetTTAModel
+
+tta_model = dict(
+    type=DetTTAModel,
+    tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.6), max_per_img=100))
+
+img_scales = [(640, 640), (320, 320), (960, 960)]
+
+tta_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=None),
+    dict(
+        type=TestTimeAug,
+        transforms=[
+            [dict(type=Resize, scale=s, keep_ratio=True) for s in img_scales],
+            [
+                # ``RandomFlip`` must be placed before ``Pad``, otherwise
+                # bounding box coordinates after flipping cannot be
+                # recovered correctly.
+                dict(type=RandomFlip, prob=1.),
+                dict(type=RandomFlip, prob=0.)
+            ],
+            [
+                dict(
+                    type=Pad,
+                    size=(960, 960),
+                    pad_val=dict(img=(114, 114, 114))),
+            ],
+            [dict(type=LoadAnnotations, with_bbox=True)],
+            [
+                dict(
+                    type=PackDetInputs,
+                    meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                               'scale_factor', 'flip', 'flip_direction'))
+            ]
+        ])
+]

mmdet/configs/rtmdet/rtmdet_x_8xb32_300e_coco.py

+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_l_8xb32_300e_coco import *
+
+model.update(
+    dict(
+        backbone=dict(deepen_factor=1.33, widen_factor=1.25),
+        neck=dict(
+            in_channels=[320, 640, 1280], out_channels=320, num_csp_blocks=4),
+        bbox_head=dict(in_channels=320, feat_channels=320)))

mmdet/datasets/__init__.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from .ade20k import (ADE20KInstanceDataset, ADE20KPanopticDataset,
+                     ADE20KSegDataset)
+from .base_det_dataset import BaseDetDataset
+from .base_semseg_dataset import BaseSegDataset
+from .base_video_dataset import BaseVideoDataset
+from .cityscapes import CityscapesDataset
+from .coco import CocoDataset
+from .coco_caption import CocoCaptionDataset
+from .coco_panoptic import CocoPanopticDataset
+from .coco_semantic import CocoSegDataset
+from .crowdhuman import CrowdHumanDataset
+from .dataset_wrappers import ConcatDataset, MultiImageMixDataset
+from .deepfashion import DeepFashionDataset
+from .dod import DODDataset
+from .dsdl import DSDLDetDataset
+from .flickr30k import Flickr30kDataset
+from .isaid import iSAIDDataset
+from .lvis import LVISDataset, LVISV1Dataset, LVISV05Dataset
+from .mdetr_style_refcoco import MDETRStyleRefCocoDataset
+from .mot_challenge_dataset import MOTChallengeDataset
+from .objects365 import Objects365V1Dataset, Objects365V2Dataset
+from .odvg import ODVGDataset
+from .openimages import OpenImagesChallengeDataset, OpenImagesDataset
+from .refcoco import RefCocoDataset
+from .reid_dataset import ReIDDataset
+from .samplers import (AspectRatioBatchSampler, ClassAwareSampler,
+                       CustomSampleSizeSampler, GroupMultiSourceSampler,
+                       MultiSourceSampler, TrackAspectRatioBatchSampler,
+                       TrackImgSampler)
+from .utils import get_loading_pipeline
+from .v3det import V3DetDataset
+from .voc import VOCDataset
+from .wider_face import WIDERFaceDataset
+from .xml_style import XMLDataset
+from .youtube_vis_dataset import YouTubeVISDataset
+
+__all__ = [
+    'XMLDataset', 'CocoDataset', 'DeepFashionDataset', 'VOCDataset',
+    'CityscapesDataset', 'LVISDataset', 'LVISV05Dataset', 'LVISV1Dataset',
+    'WIDERFaceDataset', 'get_loading_pipeline', 'CocoPanopticDataset',
+    'MultiImageMixDataset', 'OpenImagesDataset', 'OpenImagesChallengeDataset',
+    'AspectRatioBatchSampler', 'ClassAwareSampler', 'MultiSourceSampler',
+    'GroupMultiSourceSampler', 'BaseDetDataset', 'CrowdHumanDataset',
+    'Objects365V1Dataset', 'Objects365V2Dataset', 'DSDLDetDataset',
+    'BaseVideoDataset', 'MOTChallengeDataset', 'TrackImgSampler',
+    'ReIDDataset', 'YouTubeVISDataset', 'TrackAspectRatioBatchSampler',
+    'ADE20KPanopticDataset', 'CocoCaptionDataset', 'RefCocoDataset',
+    'BaseSegDataset', 'ADE20KSegDataset', 'CocoSegDataset',
+    'ADE20KInstanceDataset', 'iSAIDDataset', 'V3DetDataset', 'ConcatDataset',
+    'ODVGDataset', 'MDETRStyleRefCocoDataset', 'DODDataset',
+    'CustomSampleSizeSampler', 'Flickr30kDataset'
+]

mmdet/datasets/ade20k.py

+# Copyright (c) OpenMMLab. All rights reserved.
+import os.path as osp
+from typing import List
+
+from mmengine import fileio
+
+from mmdet.registry import DATASETS
+from .base_semseg_dataset import BaseSegDataset
+from .coco import CocoDataset
+from .coco_panoptic import CocoPanopticDataset
+
+ADE_PALETTE = [(120, 120, 120), (180, 120, 120), (6, 230, 230), (80, 50, 50),
+               (4, 200, 3), (120, 120, 80), (140, 140, 140), (204, 5, 255),
+               (230, 230, 230), (4, 250, 7), (224, 5, 255), (235, 255, 7),
+               (150, 5, 61), (120, 120, 70), (8, 255, 51), (255, 6, 82),
+               (143, 255, 140), (204, 255, 4), (255, 51, 7), (204, 70, 3),
+               (0, 102, 200), (61, 230, 250), (255, 6, 51), (11, 102, 255),
+               (255, 7, 71), (255, 9, 224), (9, 7, 230), (220, 220, 220),
+               (255, 9, 92), (112, 9, 255), (8, 255, 214), (7, 255, 224),
+               (255, 184, 6), (10, 255, 71), (255, 41, 10), (7, 255, 255),
+               (224, 255, 8), (102, 8, 255), (255, 61, 6), (255, 194, 7),
+               (255, 122, 8), (0, 255, 20), (255, 8, 41), (255, 5, 153),
+               (6, 51, 255), (235, 12, 255), (160, 150, 20), (0, 163, 255),
+               (140, 140, 140), (250, 10, 15), (20, 255, 0), (31, 255, 0),
+               (255, 31, 0), (255, 224, 0), (153, 255, 0), (0, 0, 255),
+               (255, 71, 0), (0, 235, 255), (0, 173, 255), (31, 0, 255),
+               (11, 200, 200), (255, 82, 0), (0, 255, 245), (0, 61, 255),
+               (0, 255, 112), (0, 255, 133), (255, 0, 0), (255, 163, 0),
+               (255, 102, 0), (194, 255, 0), (0, 143, 255), (51, 255, 0),
+               (0, 82, 255), (0, 255, 41), (0, 255, 173), (10, 0, 255),
+               (173, 255, 0), (0, 255, 153), (255, 92, 0), (255, 0, 255),
+               (255, 0, 245), (255, 0, 102), (255, 173, 0), (255, 0, 20),
+               (255, 184, 184), (0, 31, 255), (0, 255, 61), (0, 71, 255),
+               (255, 0, 204), (0, 255, 194), (0, 255, 82), (0, 10, 255),
+               (0, 112, 255), (51, 0, 255), (0, 194, 255), (0, 122, 255),
+               (0, 255, 163), (255, 153, 0), (0, 255, 10), (255, 112, 0),
+               (143, 255, 0), (82, 0, 255), (163, 255, 0), (255, 235, 0),
+               (8, 184, 170), (133, 0, 255), (0, 255, 92), (184, 0, 255),
+               (255, 0, 31), (0, 184, 255), (0, 214, 255), (255, 0, 112),
+               (92, 255, 0), (0, 224, 255), (112, 224, 255), (70, 184, 160),
+               (163, 0, 255), (153, 0, 255), (71, 255, 0), (255, 0, 163),
+               (255, 204, 0), (255, 0, 143), (0, 255, 235), (133, 255, 0),
+               (255, 0, 235), (245, 0, 255), (255, 0, 122), (255, 245, 0),
+               (10, 190, 212), (214, 255, 0), (0, 204, 255), (20, 0, 255),
+               (255, 255, 0), (0, 153, 255), (0, 41, 255), (0, 255, 204),
+               (41, 0, 255), (41, 255, 0), (173, 0, 255), (0, 245, 255),
+               (71, 0, 255), (122, 0, 255), (0, 255, 184), (0, 92, 255),
+               (184, 255, 0), (0, 133, 255), (255, 214, 0), (25, 194, 194),
+               (102, 255, 0), (92, 0, 255)]
+
+
+@DATASETS.register_module()
+class ADE20KPanopticDataset(CocoPanopticDataset):
+    METAINFO = {
+        'classes':
+        ('bed', 'window', 'cabinet', 'person', 'door', 'table', 'curtain',
+         'chair', 'car', 'painting, picture', 'sofa', 'shelf', 'mirror',
+         'armchair', 'seat', 'fence', 'desk', 'wardrobe, closet, press',
+         'lamp', 'tub', 'rail', 'cushion', 'box', 'column, pillar',
+         'signboard, sign', 'chest of drawers, chest, bureau, dresser',
+         'counter', 'sink', 'fireplace', 'refrigerator, icebox', 'stairs',
+         'case, display case, showcase, vitrine',
+         'pool table, billiard table, snooker table', 'pillow',
+         'screen door, screen', 'bookcase', 'coffee table',
+         'toilet, can, commode, crapper, pot, potty, stool, throne', 'flower',
+         'book', 'bench', 'countertop', 'stove', 'palm, palm tree',
+         'kitchen island', 'computer', 'swivel chair', 'boat',
+         'arcade machine', 'bus', 'towel', 'light', 'truck', 'chandelier',
+         'awning, sunshade, sunblind', 'street lamp', 'booth', 'tv',
+         'airplane', 'clothes', 'pole',
+         'bannister, banister, balustrade, balusters, handrail',
+         'ottoman, pouf, pouffe, puff, hassock', 'bottle', 'van', 'ship',
+         'fountain', 'washer, automatic washer, washing machine',
+         'plaything, toy', 'stool', 'barrel, cask', 'basket, handbasket',
+         'bag', 'minibike, motorbike', 'oven', 'ball', 'food, solid food',
+         'step, stair', 'trade name', 'microwave', 'pot', 'animal', 'bicycle',
+         'dishwasher', 'screen', 'sculpture', 'hood, exhaust hood', 'sconce',
+         'vase', 'traffic light', 'tray', 'trash can', 'fan', 'plate',
+         'monitor', 'bulletin board', 'radiator', 'glass, drinking glass',
+         'clock', 'flag', 'wall', 'building', 'sky', 'floor', 'tree',
+         'ceiling', 'road, route', 'grass', 'sidewalk, pavement',
+         'earth, ground', 'mountain, mount', 'plant', 'water', 'house', 'sea',
+         'rug', 'field', 'rock, stone', 'base, pedestal, stand', 'sand',
+         'skyscraper', 'grandstand, covered stand', 'path', 'runway',
+         'stairway, staircase', 'river', 'bridge, span', 'blind, screen',
+         'hill', 'bar', 'hovel, hut, hutch, shack, shanty', 'tower',
+         'dirt track', 'land, ground, soil',
+         'escalator, moving staircase, moving stairway',
+         'buffet, counter, sideboard',
+         'poster, posting, placard, notice, bill, card', 'stage',
+         'conveyer belt, conveyor belt, conveyer, conveyor, transporter',
+         'canopy', 'pool', 'falls', 'tent', 'cradle', 'tank, storage tank',
+         'lake', 'blanket, cover', 'pier', 'crt screen', 'shower'),
+        'thing_classes':
+        ('bed', 'window', 'cabinet', 'person', 'door', 'table', 'curtain',
+         'chair', 'car', 'painting, picture', 'sofa', 'shelf', 'mirror',
+         'armchair', 'seat', 'fence', 'desk', 'wardrobe, closet, press',
+         'lamp', 'tub', 'rail', 'cushion', 'box', 'column, pillar',
+         'signboard, sign', 'chest of drawers, chest, bureau, dresser',
+         'counter', 'sink', 'fireplace', 'refrigerator, icebox', 'stairs',
+         'case, display case, showcase, vitrine',
+         'pool table, billiard table, snooker table', 'pillow',
+         'screen door, screen', 'bookcase', 'coffee table',
+         'toilet, can, commode, crapper, pot, potty, stool, throne', 'flower',
+         'book', 'bench', 'countertop', 'stove', 'palm, palm tree',
+         'kitchen island', 'computer', 'swivel chair', 'boat',
+         'arcade machine', 'bus', 'towel', 'light', 'truck', 'chandelier',
+         'awning, sunshade, sunblind', 'street lamp', 'booth', 'tv',
+         'airplane', 'clothes', 'pole',
+         'bannister, banister, balustrade, balusters, handrail',
+         'ottoman, pouf, pouffe, puff, hassock', 'bottle', 'van', 'ship',
+         'fountain', 'washer, automatic washer, washing machine',
+         'plaything, toy', 'stool', 'barrel, cask', 'basket, handbasket',
+         'bag', 'minibike, motorbike', 'oven', 'ball', 'food, solid food',
+         'step, stair', 'trade name', 'microwave', 'pot', 'animal', 'bicycle',
+         'dishwasher', 'screen', 'sculpture', 'hood, exhaust hood', 'sconce',
+         'vase', 'traffic light', 'tray', 'trash can', 'fan', 'plate',
+         'monitor', 'bulletin board', 'radiator', 'glass, drinking glass',
+         'clock', 'flag'),
+        'stuff_classes':
+        ('wall', 'building', 'sky', 'floor', 'tree', 'ceiling', 'road, route',
+         'grass', 'sidewalk, pavement', 'earth, ground', 'mountain, mount',
+         'plant', 'water', 'house', 'sea', 'rug', 'field', 'rock, stone',
+         'base, pedestal, stand', 'sand', 'skyscraper',
+         'grandstand, covered stand', 'path', 'runway', 'stairway, staircase',
+         'river', 'bridge, span', 'blind, screen', 'hill', 'bar',
+         'hovel, hut, hutch, shack, shanty', 'tower', 'dirt track',
+         'land, ground, soil', 'escalator, moving staircase, moving stairway',
+         'buffet, counter, sideboard',
+         'poster, posting, placard, notice, bill, card', 'stage',
+         'conveyer belt, conveyor belt, conveyer, conveyor, transporter',
+         'canopy', 'pool', 'falls', 'tent', 'cradle', 'tank, storage tank',
+         'lake', 'blanket, cover', 'pier', 'crt screen', 'shower'),
+        'palette':
+        ADE_PALETTE
+    }
+
+
+@DATASETS.register_module()
+class ADE20KInstanceDataset(CocoDataset):
+    METAINFO = {
+        'classes':
+        ('bed', 'windowpane', 'cabinet', 'person', 'door', 'table', 'curtain',
+         'chair', 'car', 'painting', 'sofa', 'shelf', 'mirror', 'armchair',
+         'seat', 'fence', 'desk', 'wardrobe', 'lamp', 'bathtub', 'railing',
+         'cushion', 'box', 'column', 'signboard', 'chest of drawers',
+         'counter', 'sink', 'fireplace', 'refrigerator', 'stairs', 'case',
+         'pool table', 'pillow', 'screen door', 'bookcase', 'coffee table',
+         'toilet', 'flower', 'book', 'bench', 'countertop', 'stove', 'palm',
+         'kitchen island', 'computer', 'swivel chair', 'boat',
+         'arcade machine', 'bus', 'towel', 'light', 'truck', 'chandelier',
+         'awning', 'streetlight', 'booth', 'television receiver', 'airplane',
+         'apparel', 'pole', 'bannister', 'ottoman', 'bottle', 'van', 'ship',
+         'fountain', 'washer', 'plaything', 'stool', 'barrel', 'basket', 'bag',
+         'minibike', 'oven', 'ball', 'food', 'step', 'trade name', 'microwave',
+         'pot', 'animal', 'bicycle', 'dishwasher', 'screen', 'sculpture',
+         'hood', 'sconce', 'vase', 'traffic light', 'tray', 'ashcan', 'fan',
+         'plate', 'monitor', 'bulletin board', 'radiator', 'glass', 'clock',
+         'flag'),
+        'palette': [(204, 5, 255), (230, 230, 230), (224, 5, 255),
+                    (150, 5, 61), (8, 255, 51), (255, 6, 82), (255, 51, 7),
+                    (204, 70, 3), (0, 102, 200), (255, 6, 51), (11, 102, 255),
+                    (255, 7, 71), (220, 220, 220), (8, 255, 214),
+                    (7, 255, 224), (255, 184, 6), (10, 255, 71), (7, 255, 255),
+                    (224, 255, 8), (102, 8, 255), (255, 61, 6), (255, 194, 7),
+                    (0, 255, 20), (255, 8, 41), (255, 5, 153), (6, 51, 255),
+                    (235, 12, 255), (0, 163, 255), (250, 10, 15), (20, 255, 0),
+                    (255, 224, 0), (0, 0, 255), (255, 71, 0), (0, 235, 255),
+                    (0, 173, 255), (0, 255, 245), (0, 255, 112), (0, 255, 133),
+                    (255, 0, 0), (255, 163, 0), (194, 255, 0), (0, 143, 255),
+                    (51, 255, 0), (0, 82, 255), (0, 255, 41), (0, 255, 173),
+                    (10, 0, 255), (173, 255, 0), (255, 92, 0), (255, 0, 245),
+                    (255, 0, 102), (255, 173, 0), (255, 0, 20), (0, 31, 255),
+                    (0, 255, 61), (0, 71, 255), (255, 0, 204), (0, 255, 194),
+                    (0, 255, 82), (0, 112, 255), (51, 0, 255), (0, 122, 255),
+                    (255, 153, 0), (0, 255, 10), (163, 255, 0), (255, 235, 0),
+                    (8, 184, 170), (184, 0, 255), (255, 0, 31), (0, 214, 255),
+                    (255, 0, 112), (92, 255, 0), (70, 184, 160), (163, 0, 255),
+                    (71, 255, 0), (255, 0, 163), (255, 204, 0), (255, 0, 143),
+                    (133, 255, 0), (255, 0, 235), (245, 0, 255), (255, 0, 122),
+                    (255, 245, 0), (214, 255, 0), (0, 204, 255), (255, 255, 0),
+                    (0, 153, 255), (0, 41, 255), (0, 255, 204), (41, 0, 255),
+                    (41, 255, 0), (173, 0, 255), (0, 245, 255), (0, 255, 184),
+                    (0, 92, 255), (184, 255, 0), (255, 214, 0), (25, 194, 194),
+                    (102, 255, 0), (92, 0, 255)],
+    }
+
+
+@DATASETS.register_module()
+class ADE20KSegDataset(BaseSegDataset):
+    """ADE20K dataset.
+
+    In segmentation map annotation for ADE20K, 0 stands for background, which
+    is not included in 150 categories. The ``img_suffix`` is fixed to '.jpg',
+    and ``seg_map_suffix`` is fixed to '.png'.
+    """
+    METAINFO = dict(
+        classes=('wall', 'building', 'sky', 'floor', 'tree', 'ceiling', 'road',
+                 'bed ', 'windowpane', 'grass', 'cabinet', 'sidewalk',
+                 'person', 'earth', 'door', 'table', 'mountain', 'plant',
+                 'curtain', 'chair', 'car', 'water', 'painting', 'sofa',
+                 'shelf', 'house', 'sea', 'mirror', 'rug', 'field', 'armchair',
+                 'seat', 'fence', 'desk', 'rock', 'wardrobe', 'lamp',
+                 'bathtub', 'railing', 'cushion', 'base', 'box', 'column',
+                 'signboard', 'chest of drawers', 'counter', 'sand', 'sink',
+                 'skyscraper', 'fireplace', 'refrigerator', 'grandstand',
+                 'path', 'stairs', 'runway', 'case', 'pool table', 'pillow',
+                 'screen door', 'stairway', 'river', 'bridge', 'bookcase',
+                 'blind', 'coffee table', 'toilet', 'flower', 'book', 'hill',
+                 'bench', 'countertop', 'stove', 'palm', 'kitchen island',
+                 'computer', 'swivel chair', 'boat', 'bar', 'arcade machine',
+                 'hovel', 'bus', 'towel', 'light', 'truck', 'tower',
+                 'chandelier', 'awning', 'streetlight', 'booth',
+                 'television receiver', 'airplane', 'dirt track', 'apparel',
+                 'pole', 'land', 'bannister', 'escalator', 'ottoman', 'bottle',
+                 'buffet', 'poster', 'stage', 'van', 'ship', 'fountain',
+                 'conveyer belt', 'canopy', 'washer', 'plaything',
+                 'swimming pool', 'stool', 'barrel', 'basket', 'waterfall',
+                 'tent', 'bag', 'minibike', 'cradle', 'oven', 'ball', 'food',
+                 'step', 'tank', 'trade name', 'microwave', 'pot', 'animal',
+                 'bicycle', 'lake', 'dishwasher', 'screen', 'blanket',
+                 'sculpture', 'hood', 'sconce', 'vase', 'traffic light',
+                 'tray', 'ashcan', 'fan', 'pier', 'crt screen', 'plate',
+                 'monitor', 'bulletin board', 'shower', 'radiator', 'glass',
+                 'clock', 'flag'),
+        palette=ADE_PALETTE)
+
+    def __init__(self,
+                 img_suffix='.jpg',
+                 seg_map_suffix='.png',
+                 return_classes=False,
+                 **kwargs) -> None:
+        self.return_classes = return_classes
+        super().__init__(
+            img_suffix=img_suffix, seg_map_suffix=seg_map_suffix, **kwargs)
+
+    def load_data_list(self) -> List[dict]:
+        """Load annotation from directory or annotation file.
+
+        Returns:
+            List[dict]: All data info of dataset.
+        """
+        data_list = []
+        img_dir = self.data_prefix.get('img_path', None)
+        ann_dir = self.data_prefix.get('seg_map_path', None)
+        for img in fileio.list_dir_or_file(
+                dir_path=img_dir,
+                list_dir=False,
+                suffix=self.img_suffix,
+                recursive=True,
+                backend_args=self.backend_args):
+            data_info = dict(img_path=osp.join(img_dir, img))
+            if ann_dir is not None:
+                seg_map = img.replace(self.img_suffix, self.seg_map_suffix)
+                data_info['seg_map_path'] = osp.join(ann_dir, seg_map)
+            data_info['label_map'] = self.label_map
+            if self.return_classes:
+                data_info['text'] = list(self._metainfo['classes'])
+            data_list.append(data_info)
+        return data_list

mmdet/datasets/api_wrappers/__init__.py

+# Copyright (c) OpenMMLab. All rights reserved.
+from .coco_api import COCO, COCOeval, COCOPanoptic
+from .cocoeval_mp import COCOevalMP
+
+__all__ = ['COCO', 'COCOeval', 'COCOPanoptic', 'COCOevalMP']

mmdet/datasets/api_wrappers/coco_api.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This file add snake case alias for coco api
+
+import warnings
+from collections import defaultdict
+from typing import List, Optional, Union
+
+import pycocotools
+from pycocotools.coco import COCO as _COCO
+from pycocotools.cocoeval import COCOeval as _COCOeval
+
+
+class COCO(_COCO):
+    """This class is almost the same as official pycocotools package.
+
+    It implements some snake case function aliases. So that the COCO class has
+    the same interface as LVIS class.
+    """
+
+    def __init__(self, annotation_file=None):
+        if getattr(pycocotools, '__version__', '0') >= '12.0.2':
+            warnings.warn(
+                'mmpycocotools is deprecated. Please install official pycocotools by "pip install pycocotools"',  # noqa: E501
+                UserWarning)
+        super().__init__(annotation_file=annotation_file)
+        self.img_ann_map = self.imgToAnns
+        self.cat_img_map = self.catToImgs
+
+    def get_ann_ids(self, img_ids=[], cat_ids=[], area_rng=[], iscrowd=None):
+        return self.getAnnIds(img_ids, cat_ids, area_rng, iscrowd)
+
+    def get_cat_ids(self, cat_names=[], sup_names=[], cat_ids=[]):
+        return self.getCatIds(cat_names, sup_names, cat_ids)
+
+    def get_img_ids(self, img_ids=[], cat_ids=[]):
+        return self.getImgIds(img_ids, cat_ids)
+
+    def load_anns(self, ids):
+        return self.loadAnns(ids)
+
+    def load_cats(self, ids):
+        return self.loadCats(ids)
+
+    def load_imgs(self, ids):
+        return self.loadImgs(ids)
+
+
+# just for the ease of import
+COCOeval = _COCOeval
+
+
+class COCOPanoptic(COCO):
+    """This wrapper is for loading the panoptic style annotation file.
+
+    The format is shown in the CocoPanopticDataset class.
+
+    Args:
+        annotation_file (str, optional): Path of annotation file.
+            Defaults to None.
+    """
+
+    def __init__(self, annotation_file: Optional[str] = None) -> None:
+        super(COCOPanoptic, self).__init__(annotation_file)
+
+    def createIndex(self) -> None:
+        """Create index."""
+        # create index
+        print('creating index...')
+        # anns stores 'segment_id -> annotation'
+        anns, cats, imgs = {}, {}, {}
+        img_to_anns, cat_to_imgs = defaultdict(list), defaultdict(list)
+        if 'annotations' in self.dataset:
+            for ann in self.dataset['annotations']:
+                for seg_ann in ann['segments_info']:
+                    # to match with instance.json
+                    seg_ann['image_id'] = ann['image_id']
+                    img_to_anns[ann['image_id']].append(seg_ann)
+                    # segment_id is not unique in coco dataset orz...
+                    # annotations from different images but
+                    # may have same segment_id
+                    if seg_ann['id'] in anns.keys():
+                        anns[seg_ann['id']].append(seg_ann)
+                    else:
+                        anns[seg_ann['id']] = [seg_ann]
+
+            # filter out annotations from other images
+            img_to_anns_ = defaultdict(list)
+            for k, v in img_to_anns.items():
+                img_to_anns_[k] = [x for x in v if x['image_id'] == k]
+            img_to_anns = img_to_anns_
+
+        if 'images' in self.dataset:
+            for img_info in self.dataset['images']:
+                img_info['segm_file'] = img_info['file_name'].replace(
+                    '.jpg', '.png')
+                imgs[img_info['id']] = img_info
+
+        if 'categories' in self.dataset:
+            for cat in self.dataset['categories']:
+                cats[cat['id']] = cat
+
+        if 'annotations' in self.dataset and 'categories' in self.dataset:
+            for ann in self.dataset['annotations']:
+                for seg_ann in ann['segments_info']:
+                    cat_to_imgs[seg_ann['category_id']].append(ann['image_id'])
+
+        print('index created!')
+
+        self.anns = anns
+        self.imgToAnns = img_to_anns
+        self.catToImgs = cat_to_imgs
+        self.imgs = imgs
+        self.cats = cats
+
+    def load_anns(self,
+                  ids: Union[List[int], int] = []) -> Optional[List[dict]]:
+        """Load anns with the specified ids.
+
+        ``self.anns`` is a list of annotation lists instead of a
+        list of annotations.
+
+        Args:
+            ids (Union[List[int], int]): Integer ids specifying anns.
+
+        Returns:
+            anns (List[dict], optional): Loaded ann objects.
+        """
+        anns = []
+
+        if hasattr(ids, '__iter__') and hasattr(ids, '__len__'):
+            # self.anns is a list of annotation lists instead of
+            # a list of annotations
+            for id in ids:
+                anns += self.anns[id]
+            return anns
+        elif type(ids) == int:
+            return self.anns[ids]