Add HRNet low-resolution checkpoint

fcn-hr48-4xb2-512x1024-80k/fcn-hr48-4xb2-512x1024-80k.py

@@ -0,0 +1,316 @@
+crop_size = (
+    256,
+    512,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        123.675,
+        116.28,
+        103.53,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        512,
+    ),
+    std=[
+        58.395,
+        57.12,
+        57.375,
+    ],
+    type='SegDataPreProcessor')
+data_root = '/dataset/cityscapes/'
+dataset_type = 'CityscapesDataset'
+default_hooks = dict(
+    checkpoint=dict(by_epoch=False, interval=4000, 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'
+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,
+]
+launcher = 'pytorch'
+load_from = 'work_dirs/fcn-hr48-4xb2-512x1024-80k/fcn-hr48-4xb2-512x1024-80k_ckpt.pth'
+log_level = 'INFO'
+log_processor = dict(by_epoch=False)
+model = dict(
+    backbone=dict(
+        extra=dict(
+            stage1=dict(
+                block='BOTTLENECK',
+                num_blocks=(4, ),
+                num_branches=1,
+                num_channels=(64, ),
+                num_modules=1),
+            stage2=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                ),
+                num_branches=2,
+                num_channels=(
+                    48,
+                    96,
+                ),
+                num_modules=1),
+            stage3=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                    4,
+                ),
+                num_branches=3,
+                num_channels=(
+                    48,
+                    96,
+                    192,
+                ),
+                num_modules=4),
+            stage4=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                    4,
+                    4,
+                ),
+                num_branches=4,
+                num_channels=(
+                    48,
+                    96,
+                    192,
+                    384,
+                ),
+                num_modules=3)),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        norm_eval=False,
+        type='HRNet'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            512,
+        ),
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        channels=720,
+        concat_input=False,
+        dropout_ratio=-1,
+        in_channels=[
+            48,
+            96,
+            192,
+            384,
+        ],
+        in_index=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        input_transform='resize_concat',
+        kernel_size=1,
+        loss_decode=dict(
+            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        num_classes=19,
+        num_convs=1,
+        type='FCNHead'),
+    pretrained='open-mmlab://msra/hrnetv2_w48',
+    test_cfg=dict(mode='whole'),
+    train_cfg=dict(),
+    type='EncoderDecoder')
+norm_cfg = dict(requires_grad=True, type='SyncBN')
+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=80000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='leftImg8bit/val', seg_map_path='gtFine/val'),
+        data_root='/dataset/cityscapes/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CityscapesDataset'),
+    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,
+        1024,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=80000, type='IterBasedTrainLoop', val_interval=8000)
+train_dataloader = dict(
+    batch_size=2,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='leftImg8bit/train', seg_map_path='gtFine/train'),
+        data_root='/dataset/cityscapes/',
+        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=(
+                    256,
+                    512,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CityscapesDataset'),
+    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=(
+        256,
+        512,
+    ), type='RandomCrop'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs'),
+]
+tta_model = dict(type='SegTTAModel')
+tta_pipeline = [
+    dict(backend_args=None, 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='leftImg8bit/val', seg_map_path='gtFine/val'),
+        data_root='/dataset/cityscapes/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                2048,
+                1024,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='CityscapesDataset'),
+    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'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = './work_dirs/fcn-hr48-4xb2-512x1024-80k'

fcn-hr48-4xb2-512x1024-80k/fcn-hr48-4xb2-512x1024-80k_ckpt.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f016b92b0c7acf787eb7ad44c726f47bb90098b61d551b50a5dbf999f7bf90d1
+size 536540243