Upload 4 files

CVRP_configs/CVRP_deeplabv3plus.py

@@ -0,0 +1,303 @@
+crop_size = (
+    512,
+    512,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        123.675,
+        116.28,
+        103.53,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        512,
+        512,
+    ),
+    std=[
+        58.395,
+        57.12,
+        57.375,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'CVRPDataset/'
+dataset_type = 'CVRPDataset'
+default_hooks = dict(
+    checkpoint=dict(
+        by_epoch=False,
+        interval=2500,
+        max_keep_ckpts=1,
+        save_best='mIoU',
+        type='CheckpointHook'),
+    logger=dict(interval=100, log_metric_by_epoch=False, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='SegVisualizationHook'))
+default_scope = 'mmseg'
+env_cfg = dict(
+    cudnn_benchmark=True,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+img_ratios = [
+    0.5,
+    0.75,
+    1.0,
+    1.25,
+    1.5,
+    1.75,
+]
+load_from = None
+log_level = 'INFO'
+log_processor = dict(by_epoch=False)
+model = dict(
+    auxiliary_head=dict(
+        align_corners=False,
+        channels=256,
+        concat_input=False,
+        dropout_ratio=0.1,
+        in_channels=1024,
+        in_index=2,
+        loss_decode=dict(
+            loss_weight=0.4, type='CrossEntropyLoss', use_sigmoid=False),
+        norm_cfg=dict(requires_grad=True, type='BN'),
+        num_classes=2,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        contract_dilation=True,
+        depth=101,
+        dilations=(
+            1,
+            1,
+            2,
+            4,
+        ),
+        norm_cfg=dict(requires_grad=True, type='BN'),
+        norm_eval=False,
+        num_stages=4,
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        strides=(
+            1,
+            2,
+            1,
+            1,
+        ),
+        style='pytorch',
+        type='ResNetV1c'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            512,
+            512,
+        ),
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        c1_channels=48,
+        c1_in_channels=256,
+        channels=512,
+        dilations=(
+            1,
+            12,
+            24,
+            36,
+        ),
+        dropout_ratio=0.1,
+        in_channels=2048,
+        in_index=3,
+        loss_decode=dict(
+            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
+        norm_cfg=dict(requires_grad=True, type='BN'),
+        num_classes=2,
+        type='DepthwiseSeparableASPPHead'),
+    pretrained='open-mmlab://resnet101_v1c',
+    test_cfg=dict(mode='whole'),
+    train_cfg=dict(),
+    type='EncoderDecoder')
+norm_cfg = dict(requires_grad=True, type='BN')
+optim_wrapper = dict(
+    clip_grad=None,
+    optimizer=dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005),
+    type='OptimWrapper')
+optimizer = dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005)
+param_scheduler = [
+    dict(
+        begin=0,
+        by_epoch=False,
+        end=160000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+randomness = dict(seed=0)
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+        'mDice',
+        'mFscore',
+    ], type='IoUMetric')
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        2048,
+        1024,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=20000, type='IterBasedTrainLoop', val_interval=500)
+train_dataloader = dict(
+    batch_size=4,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    2048,
+                    1024,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    512,
+                    512,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='InfiniteSampler'))
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        keep_ratio=True,
+        ratio_range=(
+            0.5,
+            2.0,
+        ),
+        scale=(
+            2048,
+            1024,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        512,
+        512,
+    ), type='RandomCrop'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs'),
+]
+tta_model = dict(type='SegTTAModel')
+tta_pipeline = [
+    dict(file_client_args=dict(backend='disk'), type='LoadImageFromFile'),
+    dict(
+        transforms=[
+            [
+                dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
+                dict(keep_ratio=True, scale_factor=0.75, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.25, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.75, type='Resize'),
+            ],
+            [
+                dict(direction='horizontal', prob=0.0, type='RandomFlip'),
+                dict(direction='horizontal', prob=1.0, type='RandomFlip'),
+            ],
+            [
+                dict(type='LoadAnnotations'),
+            ],
+            [
+                dict(type='PackSegInputs'),
+            ],
+        ],
+        type='TestTimeAug'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+        'mDice',
+        'mFscore',
+    ], type='IoUMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = './work_dirs/CVRP_deeplabv3plus'

CVRP_configs/CVRP_knet.py

@@ -0,0 +1,404 @@
+checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window7_224_22k_20220308-d5bdebaf.pth'
+conv_kernel_size = 1
+crop_size = (
+    512,
+    512,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        123.675,
+        116.28,
+        103.53,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        512,
+        512,
+    ),
+    std=[
+        58.395,
+        57.12,
+        57.375,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'CVRPDataset/'
+dataset_type = 'CVRPDataset'
+default_hooks = dict(
+    checkpoint=dict(
+        by_epoch=False,
+        interval=2500,
+        max_keep_ckpts=1,
+        save_best='mIoU',
+        type='CheckpointHook'),
+    logger=dict(interval=100, log_metric_by_epoch=False, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='SegVisualizationHook'))
+default_scope = 'mmseg'
+env_cfg = dict(
+    cudnn_benchmark=True,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+img_ratios = [
+    0.5,
+    0.75,
+    1.0,
+    1.25,
+    1.5,
+    1.75,
+]
+load_from = None
+log_level = 'INFO'
+log_processor = dict(by_epoch=False)
+model = dict(
+    auxiliary_head=dict(
+        align_corners=False,
+        channels=256,
+        concat_input=False,
+        dropout_ratio=0.1,
+        in_channels=768,
+        in_index=2,
+        loss_decode=dict(
+            loss_weight=0.4, type='CrossEntropyLoss', use_sigmoid=False),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        num_classes=2,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        attn_drop_rate=0.0,
+        depths=[
+            2,
+            2,
+            18,
+            2,
+        ],
+        drop_path_rate=0.3,
+        drop_rate=0.0,
+        embed_dims=192,
+        mlp_ratio=4,
+        num_heads=[
+            6,
+            12,
+            24,
+            48,
+        ],
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        patch_norm=True,
+        qk_scale=None,
+        qkv_bias=True,
+        type='SwinTransformer',
+        use_abs_pos_embed=False,
+        window_size=7),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            512,
+            512,
+        ),
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        kernel_generate_head=dict(
+            align_corners=False,
+            channels=512,
+            dropout_ratio=0.1,
+            in_channels=[
+                192,
+                384,
+                768,
+                1536,
+            ],
+            in_index=[
+                0,
+                1,
+                2,
+                3,
+            ],
+            loss_decode=dict(
+                loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
+            norm_cfg=dict(requires_grad=True, type='SyncBN'),
+            num_classes=2,
+            pool_scales=(
+                1,
+                2,
+                3,
+                6,
+            ),
+            type='UPerHead'),
+        kernel_update_head=[
+            dict(
+                conv_kernel_size=1,
+                dropout=0.0,
+                feat_transform_cfg=dict(
+                    act_cfg=None, conv_cfg=dict(type='Conv2d')),
+                feedforward_channels=2048,
+                ffn_act_cfg=dict(inplace=True, type='ReLU'),
+                in_channels=512,
+                kernel_updator_cfg=dict(
+                    act_cfg=dict(inplace=True, type='ReLU'),
+                    feat_channels=256,
+                    in_channels=256,
+                    norm_cfg=dict(type='LN'),
+                    out_channels=256,
+                    type='KernelUpdator'),
+                num_classes=150,
+                num_ffn_fcs=2,
+                num_heads=8,
+                num_mask_fcs=1,
+                out_channels=512,
+                type='KernelUpdateHead',
+                with_ffn=True),
+            dict(
+                conv_kernel_size=1,
+                dropout=0.0,
+                feat_transform_cfg=dict(
+                    act_cfg=None, conv_cfg=dict(type='Conv2d')),
+                feedforward_channels=2048,
+                ffn_act_cfg=dict(inplace=True, type='ReLU'),
+                in_channels=512,
+                kernel_updator_cfg=dict(
+                    act_cfg=dict(inplace=True, type='ReLU'),
+                    feat_channels=256,
+                    in_channels=256,
+                    norm_cfg=dict(type='LN'),
+                    out_channels=256,
+                    type='KernelUpdator'),
+                num_classes=150,
+                num_ffn_fcs=2,
+                num_heads=8,
+                num_mask_fcs=1,
+                out_channels=512,
+                type='KernelUpdateHead',
+                with_ffn=True),
+            dict(
+                conv_kernel_size=1,
+                dropout=0.0,
+                feat_transform_cfg=dict(
+                    act_cfg=None, conv_cfg=dict(type='Conv2d')),
+                feedforward_channels=2048,
+                ffn_act_cfg=dict(inplace=True, type='ReLU'),
+                in_channels=512,
+                kernel_updator_cfg=dict(
+                    act_cfg=dict(inplace=True, type='ReLU'),
+                    feat_channels=256,
+                    in_channels=256,
+                    norm_cfg=dict(type='LN'),
+                    out_channels=256,
+                    type='KernelUpdator'),
+                num_classes=150,
+                num_ffn_fcs=2,
+                num_heads=8,
+                num_mask_fcs=1,
+                out_channels=512,
+                type='KernelUpdateHead',
+                with_ffn=True),
+        ],
+        num_stages=3,
+        type='IterativeDecodeHead'),
+    pretrained=
+    'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window7_224_22k_20220308-d5bdebaf.pth',
+    test_cfg=dict(mode='whole'),
+    train_cfg=dict(),
+    type='EncoderDecoder')
+norm_cfg = dict(requires_grad=True, type='BN')
+num_stages = 3
+optim_wrapper = dict(
+    clip_grad=dict(max_norm=1, norm_type=2),
+    optimizer=dict(
+        betas=(
+            0.9,
+            0.999,
+        ), lr=6e-05, type='AdamW', weight_decay=0.0005),
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            absolute_pos_embed=dict(decay_mult=0.0),
+            norm=dict(decay_mult=0.0),
+            relative_position_bias_table=dict(decay_mult=0.0))),
+    type='OptimWrapper')
+optimizer = dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005)
+param_scheduler = [
+    dict(
+        begin=0, by_epoch=False, end=1000, start_factor=0.001,
+        type='LinearLR'),
+    dict(
+        begin=1000,
+        by_epoch=False,
+        end=80000,
+        milestones=[
+            60000,
+            72000,
+        ],
+        type='MultiStepLR'),
+]
+randomness = dict(seed=0)
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+        'mDice',
+        'mFscore',
+    ], type='IoUMetric')
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        2048,
+        1024,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=20000, type='IterBasedTrainLoop', val_interval=500)
+train_dataloader = dict(
+    batch_size=2,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    2048,
+                    1024,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    512,
+                    512,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='InfiniteSampler'))
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        keep_ratio=True,
+        ratio_range=(
+            0.5,
+            2.0,
+        ),
+        scale=(
+            2048,
+            1024,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        512,
+        512,
+    ), type='RandomCrop'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs'),
+]
+tta_model = dict(type='SegTTAModel')
+tta_pipeline = [
+    dict(file_client_args=dict(backend='disk'), type='LoadImageFromFile'),
+    dict(
+        transforms=[
+            [
+                dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
+                dict(keep_ratio=True, scale_factor=0.75, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.25, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.75, type='Resize'),
+            ],
+            [
+                dict(direction='horizontal', prob=0.0, type='RandomFlip'),
+                dict(direction='horizontal', prob=1.0, type='RandomFlip'),
+            ],
+            [
+                dict(type='LoadAnnotations'),
+            ],
+            [
+                dict(type='PackSegInputs'),
+            ],
+        ],
+        type='TestTimeAug'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+        'mDice',
+        'mFscore',
+    ], type='IoUMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = './work_dirs/CVRP_knet'

CVRP_configs/CVRP_mask2former.py

@@ -0,0 +1,572 @@
+auto_scale_lr = dict(base_batch_size=16, enable=False)
+backbone_embed_multi = dict(decay_mult=0.0, lr_mult=0.1)
+backbone_norm_multi = dict(decay_mult=0.0, lr_mult=0.1)
+crop_size = (
+    512,
+    512,
+)
+custom_keys = dict({
+    'absolute_pos_embed':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone':
+    dict(decay_mult=1.0, lr_mult=0.1),
+    'backbone.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.patch_embed.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.0.blocks.0.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.0.blocks.1.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.0.downsample.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.1.blocks.0.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.1.blocks.1.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.1.downsample.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.0.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.1.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.10.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.11.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.12.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.13.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.14.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.15.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.16.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.17.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.2.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.3.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.4.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.5.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.6.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.7.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.8.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.blocks.9.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.2.downsample.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.3.blocks.0.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'backbone.stages.3.blocks.1.norm':
+    dict(decay_mult=0.0, lr_mult=0.1),
+    'level_embed':
+    dict(decay_mult=0.0, lr_mult=1.0),
+    'query_embed':
+    dict(decay_mult=0.0, lr_mult=1.0),
+    'query_feat':
+    dict(decay_mult=0.0, lr_mult=1.0),
+    'relative_position_bias_table':
+    dict(decay_mult=0.0, lr_mult=0.1)
+})
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        123.675,
+        116.28,
+        103.53,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        640,
+        640,
+    ),
+    std=[
+        58.395,
+        57.12,
+        57.375,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'CVRPDataset/'
+dataset_type = 'CVRPDataset'
+default_hooks = dict(
+    checkpoint=dict(
+        by_epoch=False,
+        interval=2500,
+        max_keep_ckpts=1,
+        save_best='mIoU',
+        type='CheckpointHook'),
+    logger=dict(interval=100, log_metric_by_epoch=False, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='SegVisualizationHook'))
+default_scope = 'mmseg'
+depths = [
+    2,
+    2,
+    18,
+    2,
+]
+embed_multi = dict(decay_mult=0.0, lr_mult=1.0)
+env_cfg = dict(
+    cudnn_benchmark=True,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+img_ratios = [
+    0.5,
+    0.75,
+    1.0,
+    1.25,
+    1.5,
+    1.75,
+]
+load_from = None
+log_level = 'INFO'
+log_processor = dict(by_epoch=False)
+model = dict(
+    backbone=dict(
+        attn_drop_rate=0.0,
+        depths=[
+            2,
+            2,
+            18,
+            2,
+        ],
+        drop_path_rate=0.3,
+        drop_rate=0.0,
+        embed_dims=192,
+        frozen_stages=-1,
+        init_cfg=dict(
+            checkpoint=
+            'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window12_384_22k_20220412-6580f57d.pth',
+            type='Pretrained'),
+        mlp_ratio=4,
+        num_heads=[
+            6,
+            12,
+            24,
+            48,
+        ],
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        patch_norm=True,
+        pretrain_img_size=384,
+        qk_scale=None,
+        qkv_bias=True,
+        type='SwinTransformer',
+        window_size=12,
+        with_cp=False),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            512,
+            512,
+        ),
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        enforce_decoder_input_project=False,
+        feat_channels=256,
+        in_channels=[
+            192,
+            384,
+            768,
+            1536,
+        ],
+        loss_cls=dict(
+            class_weight=[
+                1.0,
+                1.0,
+                0.1,
+            ],
+            loss_weight=2.0,
+            reduction='mean',
+            type='mmdet.CrossEntropyLoss',
+            use_sigmoid=False),
+        loss_dice=dict(
+            activate=True,
+            eps=1.0,
+            loss_weight=5.0,
+            naive_dice=True,
+            reduction='mean',
+            type='mmdet.DiceLoss',
+            use_sigmoid=True),
+        loss_mask=dict(
+            loss_weight=5.0,
+            reduction='mean',
+            type='mmdet.CrossEntropyLoss',
+            use_sigmoid=True),
+        num_classes=2,
+        num_queries=100,
+        num_transformer_feat_level=3,
+        out_channels=256,
+        pixel_decoder=dict(
+            act_cfg=dict(type='ReLU'),
+            encoder=dict(
+                init_cfg=None,
+                layer_cfg=dict(
+                    ffn_cfg=dict(
+                        act_cfg=dict(inplace=True, type='ReLU'),
+                        embed_dims=256,
+                        feedforward_channels=1024,
+                        ffn_drop=0.0,
+                        num_fcs=2),
+                    self_attn_cfg=dict(
+                        batch_first=True,
+                        dropout=0.0,
+                        embed_dims=256,
+                        im2col_step=64,
+                        init_cfg=None,
+                        norm_cfg=None,
+                        num_heads=8,
+                        num_levels=3,
+                        num_points=4)),
+                num_layers=6),
+            init_cfg=None,
+            norm_cfg=dict(num_groups=32, type='GN'),
+            num_outs=3,
+            positional_encoding=dict(normalize=True, num_feats=128),
+            type='mmdet.MSDeformAttnPixelDecoder'),
+        positional_encoding=dict(normalize=True, num_feats=128),
+        strides=[
+            4,
+            8,
+            16,
+            32,
+        ],
+        train_cfg=dict(
+            assigner=dict(
+                match_costs=[
+                    dict(type='mmdet.ClassificationCost', weight=2.0),
+                    dict(
+                        type='mmdet.CrossEntropyLossCost',
+                        use_sigmoid=True,
+                        weight=5.0),
+                    dict(
+                        eps=1.0,
+                        pred_act=True,
+                        type='mmdet.DiceCost',
+                        weight=5.0),
+                ],
+                type='mmdet.HungarianAssigner'),
+            importance_sample_ratio=0.75,
+            num_points=12544,
+            oversample_ratio=3.0,
+            sampler=dict(type='mmdet.MaskPseudoSampler')),
+        transformer_decoder=dict(
+            init_cfg=None,
+            layer_cfg=dict(
+                cross_attn_cfg=dict(
+                    attn_drop=0.0,
+                    batch_first=True,
+                    dropout_layer=None,
+                    embed_dims=256,
+                    num_heads=8,
+                    proj_drop=0.0),
+                ffn_cfg=dict(
+                    act_cfg=dict(inplace=True, type='ReLU'),
+                    add_identity=True,
+                    dropout_layer=None,
+                    embed_dims=256,
+                    feedforward_channels=2048,
+                    ffn_drop=0.0,
+                    num_fcs=2),
+                self_attn_cfg=dict(
+                    attn_drop=0.0,
+                    batch_first=True,
+                    dropout_layer=None,
+                    embed_dims=256,
+                    num_heads=8,
+                    proj_drop=0.0)),
+            num_layers=9,
+            return_intermediate=True),
+        type='Mask2FormerHead'),
+    test_cfg=dict(mode='whole'),
+    train_cfg=dict(),
+    type='EncoderDecoder')
+norm_cfg = dict(requires_grad=True, type='BN')
+num_classes = 150
+optim_wrapper = dict(
+    clip_grad=dict(max_norm=0.01, norm_type=2),
+    optimizer=dict(
+        betas=(
+            0.9,
+            0.999,
+        ),
+        eps=1e-08,
+        lr=0.0001,
+        type='AdamW',
+        weight_decay=0.05),
+    paramwise_cfg=dict(
+        custom_keys=dict({
+            'absolute_pos_embed':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone':
+            dict(decay_mult=1.0, lr_mult=0.1),
+            'backbone.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.patch_embed.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.0.blocks.0.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.0.blocks.1.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.0.downsample.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.1.blocks.0.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.1.blocks.1.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.1.downsample.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.0.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.1.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.10.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.11.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.12.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.13.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.14.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.15.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.16.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.17.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.2.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.3.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.4.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.5.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.6.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.7.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.8.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.blocks.9.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.2.downsample.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.3.blocks.0.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'backbone.stages.3.blocks.1.norm':
+            dict(decay_mult=0.0, lr_mult=0.1),
+            'level_embed':
+            dict(decay_mult=0.0, lr_mult=1.0),
+            'query_embed':
+            dict(decay_mult=0.0, lr_mult=1.0),
+            'query_feat':
+            dict(decay_mult=0.0, lr_mult=1.0),
+            'relative_position_bias_table':
+            dict(decay_mult=0.0, lr_mult=0.1)
+        }),
+        norm_decay_mult=0.0),
+    type='OptimWrapper')
+optimizer = dict(
+    betas=(
+        0.9,
+        0.999,
+    ),
+    eps=1e-08,
+    lr=0.0001,
+    type='AdamW',
+    weight_decay=0.05)
+param_scheduler = [
+    dict(
+        begin=0,
+        by_epoch=False,
+        end=160000,
+        eta_min=0,
+        power=0.9,
+        type='PolyLR'),
+]
+pretrained = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window12_384_22k_20220412-6580f57d.pth'
+randomness = dict(seed=0)
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+        'mDice',
+        'mFscore',
+    ], type='IoUMetric')
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        2048,
+        1024,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=20000, type='IterBasedTrainLoop', val_interval=500)
+train_dataloader = dict(
+    batch_size=2,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    2048,
+                    1024,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    512,
+                    512,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='InfiniteSampler'))
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        keep_ratio=True,
+        ratio_range=(
+            0.5,
+            2.0,
+        ),
+        scale=(
+            2048,
+            1024,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        512,
+        512,
+    ), type='RandomCrop'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs'),
+]
+tta_model = dict(type='SegTTAModel')
+tta_pipeline = [
+    dict(file_client_args=dict(backend='disk'), type='LoadImageFromFile'),
+    dict(
+        transforms=[
+            [
+                dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
+                dict(keep_ratio=True, scale_factor=0.75, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.25, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.75, type='Resize'),
+            ],
+            [
+                dict(direction='horizontal', prob=0.0, type='RandomFlip'),
+                dict(direction='horizontal', prob=1.0, type='RandomFlip'),
+            ],
+            [
+                dict(type='LoadAnnotations'),
+            ],
+            [
+                dict(type='PackSegInputs'),
+            ],
+        ],
+        type='TestTimeAug'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+        'mDice',
+        'mFscore',
+    ], type='IoUMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = './work_dirs/CVRP_mask2former'

CVRP_configs/CVRP_segformer.py

@@ -0,0 +1,322 @@
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b5_20220624-658746d9.pth'
+crop_size = (
+    512,
+    512,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        123.675,
+        116.28,
+        103.53,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        512,
+        512,
+    ),
+    std=[
+        58.395,
+        57.12,
+        57.375,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'CVRPDataset/'
+dataset_type = 'CVRPDataset'
+default_hooks = dict(
+    checkpoint=dict(
+        by_epoch=False,
+        interval=2500,
+        max_keep_ckpts=1,
+        save_best='mIoU',
+        type='CheckpointHook'),
+    logger=dict(interval=100, log_metric_by_epoch=False, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='SegVisualizationHook'))
+default_scope = 'mmseg'
+env_cfg = dict(
+    cudnn_benchmark=True,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+img_ratios = [
+    0.5,
+    0.75,
+    1.0,
+    1.25,
+    1.5,
+    1.75,
+]
+load_from = None
+log_level = 'INFO'
+log_processor = dict(by_epoch=False)
+model = dict(
+    backbone=dict(
+        attn_drop_rate=0.0,
+        drop_path_rate=0.1,
+        drop_rate=0.0,
+        embed_dims=64,
+        in_channels=3,
+        init_cfg=dict(
+            checkpoint=
+            'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b5_20220624-658746d9.pth',
+            type='Pretrained'),
+        mlp_ratio=4,
+        num_heads=[
+            1,
+            2,
+            5,
+            8,
+        ],
+        num_layers=[
+            3,
+            6,
+            40,
+            3,
+        ],
+        num_stages=4,
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        patch_sizes=[
+            7,
+            3,
+            3,
+            3,
+        ],
+        qkv_bias=True,
+        sr_ratios=[
+            8,
+            4,
+            2,
+            1,
+        ],
+        type='MixVisionTransformer'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            512,
+            512,
+        ),
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        channels=256,
+        dropout_ratio=0.1,
+        in_channels=[
+            64,
+            128,
+            320,
+            512,
+        ],
+        in_index=[
+            0,
+            1,
+            2,
+            3,
+        ],
+        loss_decode=dict(
+            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
+        norm_cfg=dict(requires_grad=True, type='BN'),
+        num_classes=2,
+        type='SegformerHead'),
+    pretrained=None,
+    test_cfg=dict(mode='whole'),
+    train_cfg=dict(),
+    type='EncoderDecoder')
+norm_cfg = dict(requires_grad=True, type='BN')
+optim_wrapper = dict(
+    optimizer=dict(
+        betas=(
+            0.9,
+            0.999,
+        ), lr=6e-05, type='AdamW', weight_decay=0.01),
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            head=dict(lr_mult=10.0),
+            norm=dict(decay_mult=0.0),
+            pos_block=dict(decay_mult=0.0))),
+    type='OptimWrapper')
+optimizer = dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005)
+param_scheduler = [
+    dict(
+        begin=0, by_epoch=False, end=1500, start_factor=1e-06,
+        type='LinearLR'),
+    dict(
+        begin=1500,
+        by_epoch=False,
+        end=160000,
+        eta_min=0.0,
+        power=1.0,
+        type='PolyLR'),
+]
+randomness = dict(seed=0)
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+        'mDice',
+        'mFscore',
+    ], type='IoUMetric')
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        2048,
+        1024,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=20000, type='IterBasedTrainLoop', val_interval=500)
+train_dataloader = dict(
+    batch_size=2,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    2048,
+                    1024,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    512,
+                    512,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='InfiniteSampler'))
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        keep_ratio=True,
+        ratio_range=(
+            0.5,
+            2.0,
+        ),
+        scale=(
+            2048,
+            1024,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        512,
+        512,
+    ), type='RandomCrop'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs'),
+]
+tta_model = dict(type='SegTTAModel')
+tta_pipeline = [
+    dict(file_client_args=dict(backend='disk'), type='LoadImageFromFile'),
+    dict(
+        transforms=[
+            [
+                dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
+                dict(keep_ratio=True, scale_factor=0.75, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.25, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
+                dict(keep_ratio=True, scale_factor=1.75, type='Resize'),
+            ],
+            [
+                dict(direction='horizontal', prob=0.0, type='RandomFlip'),
+                dict(direction='horizontal', prob=1.0, type='RandomFlip'),
+            ],
+            [
+                dict(type='LoadAnnotations'),
+            ],
+            [
+                dict(type='PackSegInputs'),
+            ],
+        ],
+        type='TestTimeAug'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        data_root='CVRPDataset/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CVRPDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+        'mDice',
+        'mFscore',
+    ], type='IoUMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = './work_dirs/CVRP_segformer'