update

app.py

@@ -0,0 +1,62 @@
+import os
+
+import torch
+import torch.nn.functional as F
+import torchvision.transforms as T
+from mmdet.apis import init_detector, inference_detector, show_result_pyplot
+import mmcv
+
+import gradio as gr
+from huggingface_hub import hf_hub_download
+
+# Device on which to run the model
+# Set to cuda to load on GPU
+device = "cpu"
+checkpoint_file = hf_hub_download(repo_id="Andy1621/uniformer", filename="mask_rcnn_3x_ms_hybrid_small.pth")
+config_file = './exp/mask_rcnn_3x_ms_hybrid_small/config.py'
+# init detector
+# build the model from a config file and a checkpoint file
+model = init_detector(config_file, checkpoint_file, device='cuda:0')
+
+
+def set_example_image(example: list) -> dict:
+    return gr.Image.update(value=example[0])
+
+
+def inference(img):
+    result = inference_detector(model, img)
+    res_img = show_result_pyplot(model, img, result).numpy()
+    return res_img
+
+
+demo = gr.Blocks()
+with demo:
+    gr.Markdown(
+        """
+        # UniFormer-S
+        Gradio demo for <a href='https://github.com/Sense-X/UniFormer' target='_blank'>UniFormer</a>: To use it, simply upload your image, or click one of the examples to load them. Read more at the links below.
+        """
+    )
+
+    with gr.Box():
+        with gr.Row():
+                with gr.Column():
+                    with gr.Row():
+                        input_image = gr.Image(label='Input Image', type='pil')
+                    with gr.Row():
+                        submit_button = gr.Button('Submit')
+                with gr.Column():
+                    res_image = gr.Image(type='numpy', label='Detection Resutls')
+        with gr.Row():
+            example_images = gr.Dataset(components=[input_image], samples=[['demp']])
+
+    gr.Markdown(
+        """
+        <p style='text-align: center'><a href='https://arxiv.org/abs/2201.09450' target='_blank'>UniFormer: Unifying Convolution and Self-attention for Visual Recognition</a> | <a href='https://github.com/Sense-X/UniFormer' target='_blank'>Github Repo</a></p>
+        """
+    )
+
+    submit_button.click(fn=inference, inputs=input_image, outputs=res_image)
+    example_images.click(fn=set_example_image, inputs=example_images, outputs=example_images.components)
+
+demo.launch(enable_queue=True)

configs/_base_/datasets/cityscapes_detection.py

@@ -0,0 +1,55 @@
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='Resize', img_scale=[(2048, 800), (2048, 1024)], keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 1024),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=1,
+    workers_per_gpu=2,
+    train=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            ann_file=data_root +
+            'annotations/instancesonly_filtered_gtFine_train.json',
+            img_prefix=data_root + 'leftImg8bit/train/',
+            pipeline=train_pipeline)),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_val.json',
+        img_prefix=data_root + 'leftImg8bit/val/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_test.json',
+        img_prefix=data_root + 'leftImg8bit/test/',
+        pipeline=test_pipeline))
+evaluation = dict(interval=1, metric='bbox')

configs/_base_/datasets/cityscapes_instance.py

@@ -0,0 +1,55 @@
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='Resize', img_scale=[(2048, 800), (2048, 1024)], keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 1024),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=1,
+    workers_per_gpu=2,
+    train=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            ann_file=data_root +
+            'annotations/instancesonly_filtered_gtFine_train.json',
+            img_prefix=data_root + 'leftImg8bit/train/',
+            pipeline=train_pipeline)),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_val.json',
+        img_prefix=data_root + 'leftImg8bit/val/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_test.json',
+        img_prefix=data_root + 'leftImg8bit/test/',
+        pipeline=test_pipeline))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/coco_detection.py

@@ -0,0 +1,48 @@
+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)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_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/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+evaluation = dict(interval=1, metric='bbox')

configs/_base_/datasets/coco_instance.py

@@ -0,0 +1,48 @@
+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)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_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/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/coco_instance_semantic.py

@@ -0,0 +1,53 @@
+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)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='SegRescale', scale_factor=1 / 8),
+    dict(type='DefaultFormatBundle'),
+    dict(
+        type='Collect',
+        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_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/',
+        seg_prefix=data_root + 'stuffthingmaps/train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/deepfashion.py

@@ -0,0 +1,53 @@
+# dataset settings
+dataset_type = 'DeepFashionDataset'
+data_root = 'data/DeepFashion/In-shop/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', img_scale=(750, 1101), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(750, 1101),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=1,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/DeepFashion_segmentation_query.json',
+        img_prefix=data_root + 'Img/',
+        pipeline=train_pipeline,
+        data_root=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/DeepFashion_segmentation_query.json',
+        img_prefix=data_root + 'Img/',
+        pipeline=test_pipeline,
+        data_root=data_root),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root +
+        'annotations/DeepFashion_segmentation_gallery.json',
+        img_prefix=data_root + 'Img/',
+        pipeline=test_pipeline,
+        data_root=data_root))
+evaluation = dict(interval=5, metric=['bbox', 'segm'])

configs/_base_/datasets/lvis_v0.5_instance.py

@@ -0,0 +1,23 @@
+_base_ = 'coco_instance.py'
+dataset_type = 'LVISV05Dataset'
+data_root = 'data/lvis_v0.5/'
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        _delete_=True,
+        type='ClassBalancedDataset',
+        oversample_thr=1e-3,
+        dataset=dict(
+            type=dataset_type,
+            ann_file=data_root + 'annotations/lvis_v0.5_train.json',
+            img_prefix=data_root + 'train2017/')),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/lvis_v0.5_val.json',
+        img_prefix=data_root + 'val2017/'),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/lvis_v0.5_val.json',
+        img_prefix=data_root + 'val2017/'))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/lvis_v1_instance.py

@@ -0,0 +1,23 @@
+_base_ = 'coco_instance.py'
+dataset_type = 'LVISV1Dataset'
+data_root = 'data/lvis_v1/'
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        _delete_=True,
+        type='ClassBalancedDataset',
+        oversample_thr=1e-3,
+        dataset=dict(
+            type=dataset_type,
+            ann_file=data_root + 'annotations/lvis_v1_train.json',
+            img_prefix=data_root)),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/lvis_v1_val.json',
+        img_prefix=data_root),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/lvis_v1_val.json',
+        img_prefix=data_root))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/voc0712.py

@@ -0,0 +1,55 @@
+# dataset settings
+dataset_type = 'VOCDataset'
+data_root = 'data/VOCdevkit/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1000, 600),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type='RepeatDataset',
+        times=3,
+        dataset=dict(
+            type=dataset_type,
+            ann_file=[
+                data_root + 'VOC2007/ImageSets/Main/trainval.txt',
+                data_root + 'VOC2012/ImageSets/Main/trainval.txt'
+            ],
+            img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
+            pipeline=train_pipeline)),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
+        img_prefix=data_root + 'VOC2007/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
+        img_prefix=data_root + 'VOC2007/',
+        pipeline=test_pipeline))
+evaluation = dict(interval=1, metric='mAP')

configs/_base_/datasets/wider_face.py

@@ -0,0 +1,63 @@
+# dataset settings
+dataset_type = 'WIDERFaceDataset'
+data_root = 'data/WIDERFace/'
+img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile', to_float32=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PhotoMetricDistortion',
+        brightness_delta=32,
+        contrast_range=(0.5, 1.5),
+        saturation_range=(0.5, 1.5),
+        hue_delta=18),
+    dict(
+        type='Expand',
+        mean=img_norm_cfg['mean'],
+        to_rgb=img_norm_cfg['to_rgb'],
+        ratio_range=(1, 4)),
+    dict(
+        type='MinIoURandomCrop',
+        min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
+        min_crop_size=0.3),
+    dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(300, 300),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=False),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=60,
+    workers_per_gpu=2,
+    train=dict(
+        type='RepeatDataset',
+        times=2,
+        dataset=dict(
+            type=dataset_type,
+            ann_file=data_root + 'train.txt',
+            img_prefix=data_root + 'WIDER_train/',
+            min_size=17,
+            pipeline=train_pipeline)),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'val.txt',
+        img_prefix=data_root + 'WIDER_val/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'val.txt',
+        img_prefix=data_root + 'WIDER_val/',
+        pipeline=test_pipeline))

configs/_base_/default_runtime.py

@@ -0,0 +1,16 @@
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+custom_hooks = [dict(type='NumClassCheckHook')]
+
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/_base_/models/cascade_mask_rcnn_r50_fpn.py

@@ -0,0 +1,196 @@
+# model settings
+model = dict(
+    type='CascadeRCNN',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        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_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        type='CascadeRoIHead',
+        num_stages=3,
+        stage_loss_weights=[1, 0.5, 0.25],
+        bbox_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]),
+        bbox_head=[
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ],
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            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=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=[
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.5,
+                    neg_iou_thr=0.5,
+                    min_pos_iou=0.5,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.6,
+                    neg_iou_thr=0.6,
+                    min_pos_iou=0.6,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.7,
+                    neg_iou_thr=0.7,
+                    min_pos_iou=0.7,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False)
+        ]),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/cascade_mask_rcnn_swin_fpn.py

@@ -0,0 +1,207 @@
+# model settings
+model = dict(
+    type='CascadeRCNN',
+    pretrained=None,
+    backbone=dict(
+        type='SwinTransformer',
+        embed_dim=96,
+        depths=[2, 2, 6, 2],
+        num_heads=[3, 6, 12, 24],
+        window_size=7,
+        mlp_ratio=4.,
+        qkv_bias=True,
+        qk_scale=None,
+        drop_rate=0.,
+        attn_drop_rate=0.,
+        drop_path_rate=0.2,
+        ape=False,
+        patch_norm=True,
+        out_indices=(0, 1, 2, 3),
+        use_checkpoint=False),
+    neck=dict(
+        type='FPN',
+        in_channels=[96, 192, 384, 768],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        type='CascadeRoIHead',
+        num_stages=3,
+        stage_loss_weights=[1, 0.5, 0.25],
+        bbox_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]),
+        bbox_head=[
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ],
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            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=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg = dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_across_levels=False,
+            nms_pre=2000,
+            nms_post=2000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=[
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.5,
+                    neg_iou_thr=0.5,
+                    min_pos_iou=0.5,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.6,
+                    neg_iou_thr=0.6,
+                    min_pos_iou=0.6,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.7,
+                    neg_iou_thr=0.7,
+                    min_pos_iou=0.7,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False)
+        ]),
+    test_cfg = dict(
+        rpn=dict(
+            nms_across_levels=False,
+            nms_pre=1000,
+            nms_post=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/cascade_mask_rcnn_uniformer_fpn.py

@@ -0,0 +1,201 @@
+# model settings
+model = dict(
+    type='CascadeRCNN',
+    pretrained=None,
+    backbone=dict(
+        type='UniFormer',
+        embed_dim=[64, 128, 320, 512],
+        layers=[3, 4, 8, 3],
+        head_dim=64,
+        mlp_ratio=4.,
+        qkv_bias=True,
+        drop_rate=0.,
+        attn_drop_rate=0.,
+        drop_path_rate=0.2),
+    neck=dict(
+        type='FPN',
+        in_channels=[64, 128, 320, 512],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        type='CascadeRoIHead',
+        num_stages=3,
+        stage_loss_weights=[1, 0.5, 0.25],
+        bbox_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]),
+        bbox_head=[
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ],
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            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=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg = dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_across_levels=False,
+            nms_pre=2000,
+            nms_post=2000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=[
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.5,
+                    neg_iou_thr=0.5,
+                    min_pos_iou=0.5,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.6,
+                    neg_iou_thr=0.6,
+                    min_pos_iou=0.6,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.7,
+                    neg_iou_thr=0.7,
+                    min_pos_iou=0.7,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False)
+        ]),
+    test_cfg = dict(
+        rpn=dict(
+            nms_across_levels=False,
+            nms_pre=1000,
+            nms_post=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/cascade_rcnn_r50_fpn.py

@@ -0,0 +1,179 @@
+# model settings
+model = dict(
+    type='CascadeRCNN',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        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_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        type='CascadeRoIHead',
+        num_stages=3,
+        stage_loss_weights=[1, 0.5, 0.25],
+        bbox_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]),
+        bbox_head=[
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ]),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=[
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.5,
+                    neg_iou_thr=0.5,
+                    min_pos_iou=0.5,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.6,
+                    neg_iou_thr=0.6,
+                    min_pos_iou=0.6,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.7,
+                    neg_iou_thr=0.7,
+                    min_pos_iou=0.7,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False)
+        ]),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/fast_rcnn_r50_fpn.py

@@ -0,0 +1,62 @@
+# model settings
+model = dict(
+    type='FastRCNN',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_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]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/faster_rcnn_r50_caffe_c4.py

@@ -0,0 +1,112 @@
+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='FasterRCNN',
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe'),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        shared_head=dict(
+            type='ResLayer',
+            depth=50,
+            stage=3,
+            stride=2,
+            dilation=1,
+            style='caffe',
+            norm_cfg=norm_cfg,
+            norm_eval=True),
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=1024,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='BBoxHead',
+            with_avg_pool=True,
+            roi_feat_size=7,
+            in_channels=2048,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=6000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/faster_rcnn_r50_caffe_dc5.py

@@ -0,0 +1,103 @@
+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='FasterRCNN',
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        strides=(1, 2, 2, 1),
+        dilations=(1, 1, 1, 2),
+        out_indices=(3, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe'),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=2048,
+        feat_channels=2048,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=2048,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=2048,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms=dict(type='nms', iou_threshold=0.7),
+            nms_pre=6000,
+            max_per_img=1000,
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/faster_rcnn_r50_fpn.py

@@ -0,0 +1,107 @@
+model = dict(
+    type='FasterRCNN',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        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_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_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]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)
+        # soft-nms is also supported for rcnn testing
+        # e.g., nms=dict(type='soft_nms', iou_threshold=0.5, min_score=0.05)
+    ))

configs/_base_/models/mask_rcnn_r50_caffe_c4.py

@@ -0,0 +1,123 @@
+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='MaskRCNN',
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe'),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        shared_head=dict(
+            type='ResLayer',
+            depth=50,
+            stage=3,
+            stride=2,
+            dilation=1,
+            style='caffe',
+            norm_cfg=norm_cfg,
+            norm_eval=True),
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=1024,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='BBoxHead',
+            with_avg_pool=True,
+            roi_feat_size=7,
+            in_channels=2048,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=None,
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=0,
+            in_channels=2048,
+            conv_out_channels=256,
+            num_classes=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=14,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=6000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            max_per_img=1000,
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/mask_rcnn_r50_fpn.py

@@ -0,0 +1,120 @@
+# model settings
+model = dict(
+    type='MaskRCNN',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        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_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_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]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            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=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/mask_rcnn_swin_fpn.py

@@ -0,0 +1,127 @@
+# model settings
+model = dict(
+    type='MaskRCNN',
+    pretrained=None,
+    backbone=dict(
+        type='SwinTransformer',
+        embed_dim=96,
+        depths=[2, 2, 6, 2],
+        num_heads=[3, 6, 12, 24],
+        window_size=7,
+        mlp_ratio=4.,
+        qkv_bias=True,
+        qk_scale=None,
+        drop_rate=0.,
+        attn_drop_rate=0.,
+        drop_path_rate=0.2,
+        ape=False,
+        patch_norm=True,
+        out_indices=(0, 1, 2, 3),
+        use_checkpoint=False),
+    neck=dict(
+        type='FPN',
+        in_channels=[96, 192, 384, 768],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_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]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            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=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/mask_rcnn_uniformer_fpn.py

@@ -0,0 +1,121 @@
+# model settings
+model = dict(
+    type='MaskRCNN',
+    pretrained=None,
+    backbone=dict(
+        type='UniFormer',
+        embed_dim=[64, 128, 320, 512],
+        layers=[3, 4, 8, 3],
+        head_dim=64,
+        mlp_ratio=4.,
+        qkv_bias=True,
+        drop_rate=0.,
+        attn_drop_rate=0.,
+        drop_path_rate=0.2),
+    neck=dict(
+        type='FPN',
+        in_channels=[64, 128, 320, 512],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_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]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            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=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/retinanet_r50_fpn.py

@@ -0,0 +1,60 @@
+# model settings
+model = dict(
+    type='RetinaNet',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs='on_input',
+        num_outs=5),
+    bbox_head=dict(
+        type='RetinaHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            octave_base_scale=4,
+            scales_per_octave=3,
+            ratios=[0.5, 1.0, 2.0],
+            strides=[8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    # training and testing settings
+    train_cfg=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms', iou_threshold=0.5),
+        max_per_img=100))

configs/_base_/models/rpn_r50_caffe_c4.py

@@ -0,0 +1,56 @@
+# model settings
+model = dict(
+    type='RPN',
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='caffe'),
+    neck=None,
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0)))

configs/_base_/models/rpn_r50_fpn.py

@@ -0,0 +1,59 @@
+# model settings
+
+model = dict(
+    type='RPN',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        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_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0)))

configs/_base_/models/ssd300.py

@@ -0,0 +1,50 @@
+# model settings
+input_size = 300
+model = dict(
+    type='SingleStageDetector',
+    pretrained='open-mmlab://vgg16_caffe',
+    backbone=dict(
+        type='SSDVGG',
+        input_size=input_size,
+        depth=16,
+        with_last_pool=False,
+        ceil_mode=True,
+        out_indices=(3, 4),
+        out_feature_indices=(22, 34),
+        l2_norm_scale=20),
+    neck=None,
+    bbox_head=dict(
+        type='SSDHead',
+        in_channels=(512, 1024, 512, 256, 256, 256),
+        num_classes=80,
+        anchor_generator=dict(
+            type='SSDAnchorGenerator',
+            scale_major=False,
+            input_size=input_size,
+            basesize_ratio_range=(0.15, 0.9),
+            strides=[8, 16, 32, 64, 100, 300],
+            ratios=[[2], [2, 3], [2, 3], [2, 3], [2], [2]]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[0.1, 0.1, 0.2, 0.2])),
+    train_cfg=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.,
+            ignore_iof_thr=-1,
+            gt_max_assign_all=False),
+        smoothl1_beta=1.,
+        allowed_border=-1,
+        pos_weight=-1,
+        neg_pos_ratio=3,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        nms=dict(type='nms', iou_threshold=0.45),
+        min_bbox_size=0,
+        score_thr=0.02,
+        max_per_img=200))
+cudnn_benchmark = True

configs/_base_/schedules/schedule_1x.py

@@ -0,0 +1,11 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[8, 11])
+runner = dict(type='EpochBasedRunner', max_epochs=12)

configs/_base_/schedules/schedule_20e.py

@@ -0,0 +1,11 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[16, 19])
+runner = dict(type='EpochBasedRunner', max_epochs=20)

configs/_base_/schedules/schedule_2x.py

@@ -0,0 +1,11 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[16, 22])
+runner = dict(type='EpochBasedRunner', max_epochs=24)

configs/albu_example/README.md

@@ -0,0 +1,19 @@
+# Albu Example
+
+[OTHERS]
+
+```
+@article{2018arXiv180906839B,
+  author = {A. Buslaev, A. Parinov, E. Khvedchenya, V.~I. Iglovikov and A.~A. Kalinin},
+  title = "{Albumentations: fast and flexible image augmentations}",
+  journal = {ArXiv e-prints},
+  eprint = {1809.06839},
+  year = 2018
+}
+```
+
+## Results and Models
+
+| Backbone  | Style   | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
+|:---------:|:-------:|:-------:|:--------:|:--------------:|:------:|:-------:|:------:|:--------:|
+| R-50      | pytorch | 1x      | 4.4      | 16.6           |  38.0  | 34.5    |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/albu_example/mask_rcnn_r50_fpn_albu_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208-ab203bcd.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208_225520.log.json) |

configs/albu_example/mask_rcnn_r50_fpn_albu_1x_coco.py

@@ -0,0 +1,73 @@
+_base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+albu_train_transforms = [
+    dict(
+        type='ShiftScaleRotate',
+        shift_limit=0.0625,
+        scale_limit=0.0,
+        rotate_limit=0,
+        interpolation=1,
+        p=0.5),
+    dict(
+        type='RandomBrightnessContrast',
+        brightness_limit=[0.1, 0.3],
+        contrast_limit=[0.1, 0.3],
+        p=0.2),
+    dict(
+        type='OneOf',
+        transforms=[
+            dict(
+                type='RGBShift',
+                r_shift_limit=10,
+                g_shift_limit=10,
+                b_shift_limit=10,
+                p=1.0),
+            dict(
+                type='HueSaturationValue',
+                hue_shift_limit=20,
+                sat_shift_limit=30,
+                val_shift_limit=20,
+                p=1.0)
+        ],
+        p=0.1),
+    dict(type='JpegCompression', quality_lower=85, quality_upper=95, p=0.2),
+    dict(type='ChannelShuffle', p=0.1),
+    dict(
+        type='OneOf',
+        transforms=[
+            dict(type='Blur', blur_limit=3, p=1.0),
+            dict(type='MedianBlur', blur_limit=3, p=1.0)
+        ],
+        p=0.1),
+]
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='Albu',
+        transforms=albu_train_transforms,
+        bbox_params=dict(
+            type='BboxParams',
+            format='pascal_voc',
+            label_fields=['gt_labels'],
+            min_visibility=0.0,
+            filter_lost_elements=True),
+        keymap={
+            'img': 'image',
+            'gt_masks': 'masks',
+            'gt_bboxes': 'bboxes'
+        },
+        update_pad_shape=False,
+        skip_img_without_anno=True),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='DefaultFormatBundle'),
+    dict(
+        type='Collect',
+        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'],
+        meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
+                   'pad_shape', 'scale_factor'))
+]
+data = dict(train=dict(pipeline=train_pipeline))

configs/atss/README.md

@@ -0,0 +1,21 @@
+# Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
+
+## Introduction
+
+[ALGORITHM]
+
+```latex
+@article{zhang2019bridging,
+  title   =  {Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection},
+  author  =  {Zhang, Shifeng and Chi, Cheng and Yao, Yongqiang and Lei, Zhen and Li, Stan Z.},
+  journal =  {arXiv preprint arXiv:1912.02424},
+  year    =  {2019}
+}
+```
+
+## Results and Models
+
+| Backbone  | Style   | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
+|:---------:|:-------:|:-------:|:--------:|:--------------:|:------:|:------:|:--------:|
+| R-50      | pytorch | 1x      | 3.7      | 19.7           |  39.4  | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/atss/atss_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209-985f7bd0.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209_102539.log.json) |
+| R-101     | pytorch | 1x      | 5.6      | 12.3           |  41.5  | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/atss/atss_r101_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/atss/atss_r101_fpn_1x_coco/atss_r101_fpn_1x_20200825-dfcadd6f.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/atss/atss_r101_fpn_1x_coco/atss_r101_fpn_1x_20200825-dfcadd6f.log.json) |

configs/atss/atss_r101_fpn_1x_coco.py

@@ -0,0 +1,5 @@
+_base_ = './atss_r50_fpn_1x_coco.py'
+model = dict(
+    pretrained='torchvision://resnet101',
+    backbone=dict(depth=101),
+)

configs/atss/atss_r50_fpn_1x_coco.py

@@ -0,0 +1,62 @@
+_base_ = [
+    '../_base_/datasets/coco_detection.py',
+    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+model = dict(
+    type='ATSS',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs='on_output',
+        num_outs=5),
+    bbox_head=dict(
+        type='ATSSHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            ratios=[1.0],
+            octave_base_scale=8,
+            scales_per_octave=1,
+            strides=[8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[0.1, 0.1, 0.2, 0.2]),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
+        loss_centerness=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
+    # training and testing settings
+    train_cfg=dict(
+        assigner=dict(type='ATSSAssigner', topk=9),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms', iou_threshold=0.6),
+        max_per_img=100))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)

configs/carafe/README.md

@@ -0,0 +1,32 @@
+# CARAFE: Content-Aware ReAssembly of FEatures
+
+## Introduction
+
+[ALGORITHM]
+
+We provide config files to reproduce the object detection & instance segmentation results in the ICCV 2019 Oral paper for [CARAFE: Content-Aware ReAssembly of FEatures](https://arxiv.org/abs/1905.02188).
+
+```
+@inproceedings{Wang_2019_ICCV,
+    title = {CARAFE: Content-Aware ReAssembly of FEatures},
+    author = {Wang, Jiaqi and Chen, Kai and Xu, Rui and Liu, Ziwei and Loy, Chen Change and Lin, Dahua},
+    booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
+    month = {October},
+    year = {2019}
+}
+```
+
+## Results and Models
+
+The results on COCO 2017 val is shown in the below table.
+
+| Method               | Backbone | Style   | Lr schd | Test Proposal Num | Inf time (fps) | Box AP | Mask AP | Config | Download |
+|:--------------------:|:--------:|:-------:|:-------:|:-----------------:|:--------------:|:------:|:-------:|:------:|:--------:|
+| Faster R-CNN w/ CARAFE | R-50-FPN | pytorch | 1x      | 1000 | 16.5 | 38.6   | 38.6       | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/carafe/faster_rcnn_r50_fpn_carafe_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/carafe/faster_rcnn_r50_fpn_carafe_1x_coco/faster_rcnn_r50_fpn_carafe_1x_coco_bbox_mAP-0.386_20200504_175733-385a75b7.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/carafe/faster_rcnn_r50_fpn_carafe_1x_coco/faster_rcnn_r50_fpn_carafe_1x_coco_20200504_175733.log.json) |
+| -                      |    -     |  -      | -       | 2000 |      |        |            |  |
+| Mask R-CNN w/ CARAFE   | R-50-FPN | pytorch | 1x      | 1000 | 14.0 | 39.3   | 35.8       | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/carafe/mask_rcnn_r50_fpn_carafe_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/carafe/mask_rcnn_r50_fpn_carafe_1x_coco/mask_rcnn_r50_fpn_carafe_1x_coco_bbox_mAP-0.393__segm_mAP-0.358_20200503_135957-8687f195.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/carafe/mask_rcnn_r50_fpn_carafe_1x_coco/mask_rcnn_r50_fpn_carafe_1x_coco_20200503_135957.log.json) |
+| -                      |   -      |  -      |   -     | 2000 |      |        |            |  |
+
+## Implementation
+
+The CUDA implementation of CARAFE can be find at https://github.com/myownskyW7/CARAFE.

configs/carafe/faster_rcnn_r50_fpn_carafe_1x_coco.py

@@ -0,0 +1,50 @@
+_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
+model = dict(
+    neck=dict(
+        type='FPN_CARAFE',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5,
+        start_level=0,
+        end_level=-1,
+        norm_cfg=None,
+        act_cfg=None,
+        order=('conv', 'norm', 'act'),
+        upsample_cfg=dict(
+            type='carafe',
+            up_kernel=5,
+            up_group=1,
+            encoder_kernel=3,
+            encoder_dilation=1,
+            compressed_channels=64)))
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=64),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=64),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))

configs/carafe/mask_rcnn_r50_fpn_carafe_1x_coco.py

@@ -0,0 +1,60 @@
+_base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(
+    neck=dict(
+        type='FPN_CARAFE',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5,
+        start_level=0,
+        end_level=-1,
+        norm_cfg=None,
+        act_cfg=None,
+        order=('conv', 'norm', 'act'),
+        upsample_cfg=dict(
+            type='carafe',
+            up_kernel=5,
+            up_group=1,
+            encoder_kernel=3,
+            encoder_dilation=1,
+            compressed_channels=64)),
+    roi_head=dict(
+        mask_head=dict(
+            upsample_cfg=dict(
+                type='carafe',
+                scale_factor=2,
+                up_kernel=5,
+                up_group=1,
+                encoder_kernel=3,
+                encoder_dilation=1,
+                compressed_channels=64))))
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=64),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=64),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))

configs/cascade_rcnn/README.md

@@ -0,0 +1,55 @@
+# Cascade R-CNN: High Quality Object Detection and Instance Segmentation
+
+## Introduction
+
+[ALGORITHM]
+
+```latex
+@article{Cai_2019,
+   title={Cascade R-CNN: High Quality Object Detection and Instance Segmentation},
+   ISSN={1939-3539},
+   url={http://dx.doi.org/10.1109/tpami.2019.2956516},
+   DOI={10.1109/tpami.2019.2956516},
+   journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
+   author={Cai, Zhaowei and Vasconcelos, Nuno},
+   year={2019},
+   pages={1–1}
+}
+```
+
+## Results and models
+
+### Cascade R-CNN
+
+|    Backbone     |  Style  | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
+| :-------------: | :-----: | :-----: | :------: | :------------: | :----: |:------:|:--------:|
+|    R-50-FPN     |  caffe  |   1x    |   4.2    |                |  40.4  | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_r50_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r50_caffe_fpn_1x_coco/cascade_rcnn_r50_caffe_fpn_1x_coco_bbox_mAP-0.404_20200504_174853-b857be87.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r50_caffe_fpn_1x_coco/cascade_rcnn_r50_caffe_fpn_1x_coco_20200504_174853.log.json) |
+|    R-50-FPN     | pytorch |   1x    |   4.4    |      16.1      |  40.3  | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco/cascade_rcnn_r50_fpn_1x_coco_20200316-3dc56deb.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco/cascade_rcnn_r50_fpn_1x_coco_20200316_214748.log.json) |
+|    R-50-FPN     | pytorch |   20e   |  -       |      -         | 41.0   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_r50_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r50_fpn_20e_coco/cascade_rcnn_r50_fpn_20e_coco_bbox_mAP-0.41_20200504_175131-e9872a90.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r50_fpn_20e_coco/cascade_rcnn_r50_fpn_20e_coco_20200504_175131.log.json) |
+|    R-101-FPN    |  caffe  |   1x    |  6.2     |                | 42.3   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_r101_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r101_caffe_fpn_1x_coco/cascade_rcnn_r101_caffe_fpn_1x_coco_bbox_mAP-0.423_20200504_175649-cab8dbd5.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r101_caffe_fpn_1x_coco/cascade_rcnn_r101_caffe_fpn_1x_coco_20200504_175649.log.json) |
+|    R-101-FPN    | pytorch |   1x    |   6.4    |      13.5      |  42.0  | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco/cascade_rcnn_r101_fpn_1x_coco_20200317-0b6a2fbf.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco/cascade_rcnn_r101_fpn_1x_coco_20200317_101744.log.json) |
+|    R-101-FPN    | pytorch |   20e   |   -      |      -         |  42.5  | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_r101_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r101_fpn_20e_coco/cascade_rcnn_r101_fpn_20e_coco_bbox_mAP-0.425_20200504_231812-5057dcc5.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r101_fpn_20e_coco/cascade_rcnn_r101_fpn_20e_coco_20200504_231812.log.json) |
+| X-101-32x4d-FPN | pytorch |   1x    |   7.6    |      10.9      |  43.7  | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_1x_coco/cascade_rcnn_x101_32x4d_fpn_1x_coco_20200316-95c2deb6.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_1x_coco/cascade_rcnn_x101_32x4d_fpn_1x_coco_20200316_055608.log.json) |
+| X-101-32x4d-FPN | pytorch |   20e   |  7.6     |                | 43.7   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_20e_coco/cascade_rcnn_x101_32x4d_fpn_20e_coco_20200906_134608-9ae0a720.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_20e_coco/cascade_rcnn_x101_32x4d_fpn_20e_coco_20200906_134608.log.json) |
+| X-101-64x4d-FPN | pytorch |   1x    |  10.7    |                | 44.7   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_1x_coco/cascade_rcnn_x101_64x4d_fpn_1x_coco_20200515_075702-43ce6a30.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_1x_coco/cascade_rcnn_x101_64x4d_fpn_1x_coco_20200515_075702.log.json) |
+| X-101-64x4d-FPN | pytorch |   20e   |  10.7    |                | 44.5   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_20e_coco/cascade_rcnn_x101_64x4d_fpn_20e_coco_20200509_224357-051557b1.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_20e_coco/cascade_rcnn_x101_64x4d_fpn_20e_coco_20200509_224357.log.json)|
+
+### Cascade Mask R-CNN
+
+|    Backbone     |  Style  | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
+| :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: |
+|    R-50-FPN     |  caffe  |   1x    |  5.9     |                | 41.2   | 36.0    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_caffe_fpn_1x_coco/cascade_mask_rcnn_r50_caffe_fpn_1x_coco_bbox_mAP-0.412__segm_mAP-0.36_20200504_174659-5004b251.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_caffe_fpn_1x_coco/cascade_mask_rcnn_r50_caffe_fpn_1x_coco_20200504_174659.log.json) |
+|    R-50-FPN     | pytorch |   1x    |  6.0     |  11.2          | 41.2   | 35.9    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco/cascade_mask_rcnn_r50_fpn_1x_coco_20200203-9d4dcb24.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco/cascade_mask_rcnn_r50_fpn_1x_coco_20200203_170449.log.json) |
+|    R-50-FPN     | pytorch |   20e   |  -       | -              | 41.9   | 36.5    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco/cascade_mask_rcnn_r50_fpn_20e_coco_bbox_mAP-0.419__segm_mAP-0.365_20200504_174711-4af8e66e.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco/cascade_mask_rcnn_r50_fpn_20e_coco_20200504_174711.log.json)|
+|    R-101-FPN    |  caffe  |   1x    |  7.8     |                | 43.2   | 37.6    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_r101_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r101_caffe_fpn_1x_coco/cascade_mask_rcnn_r101_caffe_fpn_1x_coco_bbox_mAP-0.432__segm_mAP-0.376_20200504_174813-5c1e9599.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r101_caffe_fpn_1x_coco/cascade_mask_rcnn_r101_caffe_fpn_1x_coco_20200504_174813.log.json)|
+|    R-101-FPN    | pytorch |   1x    |  7.9     |  9.8           | 42.9   | 37.3    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco/cascade_mask_rcnn_r101_fpn_1x_coco_20200203-befdf6ee.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco/cascade_mask_rcnn_r101_fpn_1x_coco_20200203_092521.log.json) |
+|    R-101-FPN    | pytorch |   20e   |  -       |  -             | 43.4   | 37.8    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r101_fpn_20e_coco/cascade_mask_rcnn_r101_fpn_20e_coco_bbox_mAP-0.434__segm_mAP-0.378_20200504_174836-005947da.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r101_fpn_20e_coco/cascade_mask_rcnn_r101_fpn_20e_coco_20200504_174836.log.json)|
+| X-101-32x4d-FPN | pytorch |   1x    |  9.2     |  8.6           | 44.3   | 38.3    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco_20200201-0f411b1f.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco_20200201_052416.log.json) |
+| X-101-32x4d-FPN | pytorch |   20e   |  9.2     |   -            | 45.0   | 39.0    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_20e_coco/cascade_mask_rcnn_x101_32x4d_fpn_20e_coco_20200528_083917-ed1f4751.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_20e_coco/cascade_mask_rcnn_x101_32x4d_fpn_20e_coco_20200528_083917.log.json) |
+| X-101-64x4d-FPN | pytorch |   1x    |  12.2    |  6.7           | 45.3   | 39.2    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco_20200203-9a2db89d.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco_20200203_044059.log.json) |
+| X-101-64x4d-FPN | pytorch |   20e   |  12.2   |                 | 45.6     |39.5   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_20e_coco/cascade_mask_rcnn_x101_64x4d_fpn_20e_coco_20200512_161033-bdb5126a.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_20e_coco/cascade_mask_rcnn_x101_64x4d_fpn_20e_coco_20200512_161033.log.json)|
+
+**Notes:**
+
+- The `20e` schedule in Cascade (Mask) R-CNN indicates decreasing the lr at 16 and 19 epochs, with a total of 20 epochs.

configs/cascade_rcnn/cascade_mask_rcnn_r101_caffe_fpn_1x_coco.py

@@ -0,0 +1,4 @@
+_base_ = './cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://detectron2/resnet101_caffe',
+    backbone=dict(depth=101))

configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco.py

@@ -0,0 +1,2 @@
+_base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))

configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_20e_coco.py

@@ -0,0 +1,2 @@
+_base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py'
+model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))

configs/cascade_rcnn/cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py

@@ -0,0 +1,38 @@
+_base_ = ['./cascade_mask_rcnn_r50_fpn_1x_coco.py']
+
+model = dict(
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(
+        norm_cfg=dict(requires_grad=False), norm_eval=True, style='caffe'))
+
+img_norm_cfg = dict(
+    mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))

configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py

@@ -0,0 +1,5 @@
+_base_ = [
+    '../_base_/models/cascade_mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/coco_instance.py',
+    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]

configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco.py

@@ -0,0 +1,5 @@
+_base_ = [
+    '../_base_/models/cascade_mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/coco_instance.py',
+    '../_base_/schedules/schedule_20e.py', '../_base_/default_runtime.py'
+]

configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py

@@ -0,0 +1,13 @@
+_base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://resnext101_32x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        style='pytorch'))

configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_20e_coco.py

@@ -0,0 +1,13 @@
+_base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py'
+model = dict(
+    pretrained='open-mmlab://resnext101_32x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        style='pytorch'))

configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco.py

@@ -0,0 +1,13 @@
+_base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://resnext101_64x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        style='pytorch'))