Upload upernet_alibi_vit_tiny_512x512_ade20k.py with huggingface_hub

upernet_alibi_vit_tiny_512x512_ade20k.py

@@ -0,0 +1,319 @@
+crop_size = (
+    512,
+    512,
+)
+custom_imports = dict(
+    allow_failed_imports=False, imports=[
+        'segmentation',
+    ])
+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 = 'data/ade/ADEChallengeData2016'
+dataset_type = 'ADE20KDataset'
+default_hooks = dict(
+    checkpoint=dict(
+        by_epoch=False, interval=4000, save_best='mIoU',
+        type='CheckpointHook'),
+    logger=dict(interval=50, 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'
+depth = 12
+env_cfg = dict(
+    cudnn_benchmark=True,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+hidden_dim = 192
+launcher = 'none'
+load_from = None
+log_level = 'INFO'
+log_processor = dict(by_epoch=False)
+mlp_dim = 768
+model = dict(
+    auxiliary_head=dict(
+        align_corners=False,
+        channels=256,
+        concat_input=False,
+        dropout_ratio=0.1,
+        in_channels=192,
+        in_index=3,
+        loss_decode=dict(
+            loss_weight=0.4, type='CrossEntropyLoss', use_sigmoid=False),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        num_classes=150,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        attention_dropout=0.0,
+        depth=12,
+        dropout=0.0,
+        hidden_dim=192,
+        img_size=512,
+        in_chans=3,
+        init_cfg=dict(
+            checkpoint='checkpoints/alibi_vit_imagenet100_best.pth',
+            type='Pretrained'),
+        mlp_dim=768,
+        num_heads=3,
+        out_indices=(
+            2,
+            5,
+            8,
+            11,
+        ),
+        patch_size=16,
+        pretrain_img_size=224,
+        type='ALiBiViTBackbone'),
+    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=512,
+        dropout_ratio=0.1,
+        in_channels=[
+            192,
+            192,
+            192,
+            192,
+        ],
+        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=150,
+        pool_scales=(
+            1,
+            2,
+            3,
+            6,
+        ),
+        type='UPerHead'),
+    neck=dict(
+        in_channels=[
+            192,
+            192,
+            192,
+            192,
+        ],
+        out_channels=192,
+        scales=[
+            4,
+            2,
+            1,
+            0.5,
+        ],
+        type='MultiLevelNeck'),
+    test_cfg=dict(mode='whole'),
+    train_cfg=dict(),
+    type='EncoderDecoder')
+norm_cfg = dict(requires_grad=True, type='SyncBN')
+num_classes = 150
+num_heads = 3
+optim_wrapper = dict(
+    clip_grad=dict(max_norm=1.0, norm_type=2),
+    optimizer=dict(
+        betas=(
+            0.9,
+            0.999,
+        ), lr=0.0004, type='AdamW', weight_decay=0.05),
+    paramwise_cfg=dict(custom_keys=dict(backbone=dict(lr_mult=0.1))),
+    type='AmpOptimWrapper')
+param_scheduler = [
+    dict(
+        begin=0, by_epoch=False, end=500, start_factor=1e-06, type='LinearLR'),
+    dict(
+        begin=500,
+        by_epoch=False,
+        end=40000,
+        eta_min=0.0,
+        power=1.0,
+        type='PolyLR'),
+]
+patch_size = 16
+resume = True
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        data_root='data/ade/ADEChallengeData2016',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                512,
+            ), type='Resize'),
+            dict(reduce_zero_label=True, type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='ADE20KDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+    ], type='IoUMetric')
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        2048,
+        512,
+    ), type='Resize'),
+    dict(reduce_zero_label=True, type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=40000, type='IterBasedTrainLoop', val_interval=4000)
+train_dataloader = dict(
+    batch_size=16,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='images/training', seg_map_path='annotations/training'),
+        data_root='data/ade/ADEChallengeData2016',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(reduce_zero_label=True, type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    2048,
+                    512,
+                ),
+                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='ADE20KDataset'),
+    num_workers=8,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='InfiniteSampler'))
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(reduce_zero_label=True, type='LoadAnnotations'),
+    dict(
+        keep_ratio=True,
+        ratio_range=(
+            0.5,
+            2.0,
+        ),
+        scale=(
+            2048,
+            512,
+        ),
+        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'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        data_root='data/ade/ADEChallengeData2016',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                512,
+            ), type='Resize'),
+            dict(reduce_zero_label=True, type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='ADE20KDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    iou_metrics=[
+        'mIoU',
+    ], type='IoUMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+    dict(
+        init_kwargs=dict(
+            name='upernet_alibi_vit_tiny_512x512_ade20k',
+            project='vit-segmentation',
+            tags=[
+                'alibi_vit',
+                'ade20k',
+                'upernet',
+            ]),
+        type='WandbVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+        dict(
+            init_kwargs=dict(
+                name='upernet_alibi_vit_tiny_512x512_ade20k',
+                project='vit-segmentation',
+                tags=[
+                    'alibi_vit',
+                    'ade20k',
+                    'upernet',
+                ]),
+            type='WandbVisBackend'),
+    ])
+work_dir = './work_dirs/upernet_alibi_vit_tiny_512x512_ade20k'