Sibaja 2

configs/_base_/datasets/deepGlobe.py

@@ -0,0 +1,69 @@
+#configs/_base_/datasets/deepGlobe.py
+#mmseseg/configs/_base_/datasets/deepGlobe.py
+# dataset settings
+dataset_type = 'DeepGlobeDataset'
+data_root = 'data/deepglobe_ds/'
+crop_size = (256, 256)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(512, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(512, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=32,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='img_dir/train_sat', seg_map_path='ann_dir/train_mask_grayscale'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=16,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='img_dir/val_sat', seg_map_path='ann_dir/val_mask_grayscale'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/default_runtime.py

@@ -4,7 +4,9 @@
     mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
     dist_cfg=dict(backend='nccl'),
 )
-vis_backends = [dict(type='LocalVisBackend')]
+vis_backends = [dict(type='LocalVisBackend'),
+                dict(type='TensorboardVisBackend')]
+
 visualizer = dict(
     type='SegLocalVisualizer', vis_backends=vis_backends, name='visualizer')
 log_processor = dict(by_epoch=False)

configs/_base_/models/ccnet_r50-d8.py → configs/_base_/models/ccnet_r50-d8_deepglobe_5.py

@@ -2,8 +2,8 @@
 norm_cfg = dict(type='SyncBN', requires_grad=True)
 data_preprocessor = dict(
     type='SegDataPreProcessor',
-    mean=[123.675, 116.28, 103.53],
-    std=[58.395, 57.12, 57.375],
+    mean=[0.4082, 0.3791, 0.2815],
+    std=[0.1451, 0.1116, 0.1013],
     bgr_to_rgb=True,
     pad_val=0,
     seg_pad_val=255)
@@ -29,7 +29,7 @@
         channels=512,
         recurrence=2,
         dropout_ratio=0.1,
-        num_classes=19,
+        num_classes=7,
         norm_cfg=norm_cfg,
         align_corners=False,
         loss_decode=dict(
@@ -42,7 +42,7 @@
         num_convs=1,
         concat_input=False,
         dropout_ratio=0.1,
-        num_classes=19,
+        num_classes=7,
         norm_cfg=norm_cfg,
         align_corners=False,
         loss_decode=dict(

configs/_base_/models/deeplabv3_r50-d8.py

@@ -1,9 +1,10 @@
+#configs/_base_/models/deeplabv3_r50-d8.py
 # model settings
 norm_cfg = dict(type='SyncBN', requires_grad=True)
 data_preprocessor = dict(
     type='SegDataPreProcessor',
-    mean=[123.675, 116.28, 103.53],
-    std=[58.395, 57.12, 57.375],
+    mean=[0.4082, 0.3791, 0.2815],
+    std=[ 0.1451, 0.1116, 0.1013],
     bgr_to_rgb=True,
     pad_val=0,
     seg_pad_val=255)
@@ -29,7 +30,7 @@
         channels=512,
         dilations=(1, 12, 24, 36),
         dropout_ratio=0.1,
-        num_classes=19,
+        num_classes=7,
         norm_cfg=norm_cfg,
         align_corners=False,
         loss_decode=dict(
@@ -42,7 +43,7 @@
         num_convs=1,
         concat_input=False,
         dropout_ratio=0.1,
-        num_classes=19,
+        num_classes=7,
         norm_cfg=norm_cfg,
         align_corners=False,
         loss_decode=dict(

configs/_base_/models/deeplabv3_r50-d8_deepGlobe.py

@@ -0,0 +1,53 @@
+#configs/_base_/models/deeplabv3_r50-d8.py
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[0.4082, 0.3791, 0.2815],
+    std=[ 0.1451, 0.1116, 0.1013],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='ASPPHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        dilations=(1, 12, 24, 36),
+        dropout_ratio=0.1,
+        num_classes=7,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=7,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/deeplabv3plus_r50-d8_deepglobe.py

@@ -0,0 +1,54 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[0.4082, 0.3791, 0.2815],
+    std=[ 0.1451, 0.1116, 0.1013],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='DepthwiseSeparableASPPHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        dilations=(1, 12, 24, 36),
+        c1_in_channels=256,
+        c1_channels=48,
+        dropout_ratio=0.1,
+        num_classes=7,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=7,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/fcn_hr18_deepGlobe.py

@@ -0,0 +1,60 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[0.4082, 0.3791, 0.2815],
+    std=[ 0.1351, 0.1022, 0.0931],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://msra/hrnetv2_w18',
+    backbone=dict(
+        type='HRNet',
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        extra=dict(
+            stage1=dict(
+                num_modules=1,
+                num_branches=1,
+                block='BOTTLENECK',
+                num_blocks=(4, ),
+                num_channels=(64, )),
+            stage2=dict(
+                num_modules=1,
+                num_branches=2,
+                block='BASIC',
+                num_blocks=(4, 4),
+                num_channels=(18, 36)),
+            stage3=dict(
+                num_modules=4,
+                num_branches=3,
+                block='BASIC',
+                num_blocks=(4, 4, 4),
+                num_channels=(18, 36, 72)),
+            stage4=dict(
+                num_modules=3,
+                num_branches=4,
+                block='BASIC',
+                num_blocks=(4, 4, 4, 4),
+                num_channels=(18, 36, 72, 144)))),
+    decode_head=dict(
+        type='FCNHead',
+        in_channels=[18, 36, 72, 144],
+        in_index=(0, 1, 2, 3),
+        channels=sum([18, 36, 72, 144]),
+        input_transform='resize_concat',
+        kernel_size=1,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=-1,
+        num_classes=7,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/fcn_r50-d8deepglobe.py

@@ -0,0 +1,53 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[0.4082, 0.3791, 0.2815],
+    std=[0.1351, 0.1022, 0.0931],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='FCNHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        num_convs=2,
+        concat_input=True,
+        dropout_ratio=0.1,
+        num_classes=7,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=7,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))