Merge branch 'hepj_work' into 'main'

增加conformer代码

See merge request dcutoolkit/deeplearing/dlexamples_new!7

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_conformer_small_patch32_fpn_1x_coco.py

+_base_ = [
+    '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    type='MaskRCNN',
+    pretrained=None,
+    backbone=dict(
+            type='Conformer',
+            embed_dim=384,
+            depth=12,
+            patch_size=32,
+            channel_ratio=4,
+            num_heads=6,
+            mlp_ratio=4,
+            qkv_bias=True,
+            norm_eval=True,
+            frozen_stages=1
+        ),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 1024],
+        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_across_levels=False,
+            nms_pre=2000,
+            nms_post=1000,
+            max_num=1000,
+            nms_thr=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_across_levels=False,
+            nms_pre=1000,
+            nms_post=1000,
+            max_num=1000,
+            nms_thr=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)))
+
+
+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=(1344, 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=(1344, 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'])
+
+# optimizer
+optimizer = dict(
+    type='AdamW',
+    lr=0.0001,
+    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])
+total_epochs = 12
+
+# optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
\ No newline at end of file

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r101_caffe_fpn_1x_coco.py

+_base_ = './mask_rcnn_r50_caffe_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://detectron2/resnet101_caffe',
+    backbone=dict(depth=101))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py

+_base_ = './mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r101_fpn_2x_coco.py

+_base_ = './mask_rcnn_r50_fpn_2x_coco.py'
+model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_caffe_c4_1x_coco.py

+_base_ = [
+    '../_base_/models/mask_rcnn_r50_caffe_c4.py',
+    '../_base_/datasets/coco_instance.py',
+    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+# use caffe img_norm
+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))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_1x_coco.py

+_base_ = './mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(norm_cfg=dict(requires_grad=False), style='caffe'))
+# use caffe img_norm
+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))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_coco.py

+_base_ = './mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(norm_cfg=dict(requires_grad=False), style='caffe'))
+# use caffe img_norm
+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,
+        poly2mask=False),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco.py

+_base_ = './mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_coco.py'
+# learning policy
+lr_config = dict(step=[16, 23])
+total_epochs = 24

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco.py

+_base_ = './mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_coco.py'
+# learning policy
+lr_config = dict(step=[28, 34])
+total_epochs = 36

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain_1x_coco.py

+_base_ = './mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://detectron2/resnet50_caffe',
+    backbone=dict(norm_cfg=dict(requires_grad=False), style='caffe'))
+# use caffe img_norm
+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, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_poly_1x_coco_v1.py

+_base_ = './mask_rcnn_r50_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://resnet50_caffe_bgr',
+    backbone=dict(norm_cfg=dict(requires_grad=False), style='caffe'),
+    rpn_head=dict(
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        bbox_roi_extractor=dict(
+            roi_layer=dict(
+                type='RoIAlign',
+                output_size=7,
+                sampling_ratio=2,
+                aligned=False)),
+        bbox_head=dict(
+            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
+        mask_roi_extractor=dict(
+            roi_layer=dict(
+                type='RoIAlign',
+                output_size=14,
+                sampling_ratio=2,
+                aligned=False))))
+# use caffe img_norm
+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,
+        poly2mask=False),
+    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))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py

+_base_ = [
+    '../_base_/models/mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/coco_instance.py',
+    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_fpn_2x_coco.py

+_base_ = [
+    '../_base_/models/mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/coco_instance.py',
+    '../_base_/schedules/schedule_2x.py', '../_base_/default_runtime.py'
+]

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_r50_fpn_poly_1x_coco.py

+_base_ = [
+    '../_base_/models/mask_rcnn_r50_fpn.py',
+    '../_base_/datasets/coco_instance.py',
+    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+
+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,
+        poly2mask=False),
+    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']),
+]
+data = dict(train=dict(pipeline=train_pipeline))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py

+_base_ = './mask_rcnn_r101_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'))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_x101_32x4d_fpn_2x_coco.py

+_base_ = './mask_rcnn_r101_fpn_2x_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'))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_x101_32x8d_fpn_1x_coco.py

+_base_ = './mask_rcnn_r101_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://detectron2/resnext101_32x8d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=8,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        style='pytorch'))
+
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[103.530, 116.280, 123.675],
+    std=[57.375, 57.120, 58.395],
+    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(
+    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))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_x101_32x8d_fpn_mstrain-poly_1x_coco.py

+_base_ = './mask_rcnn_r101_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://detectron2/resnext101_32x8d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=8,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        style='pytorch'))
+
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[103.530, 116.280, 123.675],
+    std=[57.375, 57.120, 58.395],
+    to_rgb=False)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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))

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_x101_32x8d_fpn_mstrain-poly_3x_coco.py

+_base_ = './mask_rcnn_r101_fpn_1x_coco.py'
+model = dict(
+    pretrained='open-mmlab://detectron2/resnext101_32x8d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=8,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        style='pytorch'))
+
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[103.530, 116.280, 123.675],
+    std=[57.375, 57.120, 58.395],
+    to_rgb=False)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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))
+
+lr_config = dict(step=[28, 34])
+total_epochs = 36

PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/mask_rcnn_x101_64x4d_fpn_1x_coco.py

+_base_ = './mask_rcnn_x101_32x4d_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'))