open-mmlab · EmiSib · May 31, 2024 · May 31, 2024 · May 31, 2024 · May 31, 2024
diff --git a/PrediccionesCCNET/201966_sat.jpg b/PrediccionesCCNET/201966_sat.jpg
diff --git a/PrediccionesCCNET/298983_sat.jpg b/PrediccionesCCNET/298983_sat.jpg
diff --git a/PrediccionesCCNET/650673_sat.jpg b/PrediccionesCCNET/650673_sat.jpg
diff --git a/PrediccionesCCNET/802551_sat.jpg b/PrediccionesCCNET/802551_sat.jpg
diff --git a/PrediccionesCCNET/896504_sat.jpg b/PrediccionesCCNET/896504_sat.jpg
diff --git a/PrediccionesDeepLab/201966_sat.jpg b/PrediccionesDeepLab/201966_sat.jpg
diff --git a/PrediccionesDeepLab/298983_sat.jpg b/PrediccionesDeepLab/298983_sat.jpg
diff --git a/PrediccionesDeepLab/650673_sat.jpg b/PrediccionesDeepLab/650673_sat.jpg
diff --git a/PrediccionesDeepLab/802551_sat.jpg b/PrediccionesDeepLab/802551_sat.jpg
diff --git a/PrediccionesDeepLab/896504_sat.jpg b/PrediccionesDeepLab/896504_sat.jpg
diff --git a/PrediccionesFCN/201966_sat.jpg b/PrediccionesFCN/201966_sat.jpg
diff --git a/PrediccionesFCN/298983_sat.jpg b/PrediccionesFCN/298983_sat.jpg
diff --git a/PrediccionesFCN/650673_sat.jpg b/PrediccionesFCN/650673_sat.jpg
diff --git a/PrediccionesFCN/802551_sat.jpg b/PrediccionesFCN/802551_sat.jpg
diff --git a/PrediccionesFCN/896504_sat.jpg b/PrediccionesFCN/896504_sat.jpg
diff --git a/PrediccionesHRNet/201966_sat.jpg b/PrediccionesHRNet/201966_sat.jpg
diff --git a/PrediccionesHRNet/298983_sat.jpg b/PrediccionesHRNet/298983_sat.jpg
diff --git a/PrediccionesHRNet/650673_sat.jpg b/PrediccionesHRNet/650673_sat.jpg
diff --git a/PrediccionesHRNet/802551_sat.jpg b/PrediccionesHRNet/802551_sat.jpg
diff --git a/PrediccionesHRNet/896504_sat.jpg b/PrediccionesHRNet/896504_sat.jpg
diff --git a/Test_model.zip b/Test_model.zip
diff --git a/Test_model/201966_sat.jpg b/Test_model/201966_sat.jpg
diff --git a/Test_model/298983_sat.jpg b/Test_model/298983_sat.jpg
diff --git a/Test_model/650673_sat.jpg b/Test_model/650673_sat.jpg
diff --git a/Test_model/802551_sat.jpg b/Test_model/802551_sat.jpg
diff --git a/Test_model/896504_sat.jpg b/Test_model/896504_sat.jpg
diff --git a/configs/_base_/datasets/deepGlobe.py b/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
diff --git a/configs/_base_/default_runtime.py b/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)

diff --git a/configs/_base_/models/ccnet_r50-d8.py → ..._base_/models/ccnet_r50-d8_deepglobe_5.py b/configs/_base_/models/ccnet_r50-d8.py → ..._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(

diff --git a/configs/_base_/models/deeplabv3_r50-d8.py b/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(

diff --git a/configs/_base_/models/deeplabv3_r50-d8_deepGlobe.py b/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'))
diff --git a/configs/_base_/models/deeplabv3plus_r50-d8_deepglobe.py b/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'))
diff --git a/configs/_base_/models/fcn_hr18_deepGlobe.py b/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'))
diff --git a/configs/_base_/models/fcn_r50-d8deepglobe.py b/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'))
diff --git a/configs/_base_/models/gcnet_r50-d8_deepGlobe.py b/configs/_base_/models/gcnet_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='GCHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        ratio=1 / 4.,
+        pooling_type='att',
+        fusion_types=('channel_add', ),
+        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'))
diff --git a/configs/_base_/models/pspnet_unet_deepglobe_s5-d16.py b/configs/_base_/models/pspnet_unet_deepglobe_s5-d16.py
@@ -0,0 +1,58 @@
+# 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=None,
+    backbone=dict(
+        type='UNet',
+        in_channels=3,
+        base_channels=64,
+        num_stages=5,
+        strides=(1, 1, 1, 1, 1),
+        enc_num_convs=(2, 2, 2, 2, 2),
+        dec_num_convs=(2, 2, 2, 2),
+        downsamples=(True, True, True, True),
+        enc_dilations=(1, 1, 1, 1, 1),
+        dec_dilations=(1, 1, 1, 1),
+        with_cp=False,
+        conv_cfg=None,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='ReLU'),
+        upsample_cfg=dict(type='InterpConv'),
+        norm_eval=False),
+    decode_head=dict(
+        type='PSPHead',
+        in_channels=64,
+        in_index=4,
+        channels=16,
+        pool_scales=(1, 2, 3, 6),
+        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=128,
+        in_index=3,
+        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='slide', crop_size=256, stride=170))
diff --git a/configs/_base_/schedules/schedule_40k.py b/configs/_base_/schedules/schedule_40k.py
@@ -8,11 +8,11 @@
         eta_min=1e-4,
         power=0.9,
         begin=0,
-        end=40000,
+        end=10000,
         by_epoch=False)
 ]
 # training schedule for 40k
-train_cfg = dict(type='IterBasedTrainLoop', max_iters=40000, val_interval=4000)
+train_cfg = dict(type='IterBasedTrainLoop', max_iters=10000, val_interval=1000)
 val_cfg = dict(type='ValLoop')
 test_cfg = dict(type='TestLoop')
 default_hooks = dict(

diff --git a/configs/ccnet/ccnet_r50-d8_4xb2-40k_deepglobe-256x256.py b/configs/ccnet/ccnet_r50-d8_4xb2-40k_deepglobe-256x256.py
@@ -0,0 +1,7 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8_deepglobe_5.py', '../_base_/datasets/deepGlobe.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
+crop_size = (256, 256)
+data_preprocessor = dict(size=crop_size)
+model = dict(data_preprocessor=data_preprocessor)
diff --git a/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_deepglobe-512x1024.py b/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_deepglobe-512x1024.py
@@ -0,0 +1,8 @@
+#configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_deepglobe-512x1024.py
+_base_ = [
+    '../_base_/models/deeplabv3_r50-d8_deepGlobe.py', '../_base_/datasets/deepGlobe.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
+crop_size = (256, 256)
+data_preprocessor = dict(size=crop_size)
+model = dict(data_preprocessor=data_preprocessor)
diff --git a/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_deepglobe-512x1024.py b/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_deepglobe-512x1024.py
@@ -0,0 +1,8 @@
+_base_ = [
+    '../_base_/models/deeplabv3plus_r50-d8_deepglobe.py',
+    '../_base_/datasets/deepglobe.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_40k.py'
+]
+crop_size = (256, 256)
+data_preprocessor = dict(size=crop_size)
+model = dict(data_preprocessor=data_preprocessor)
diff --git a/configs/fcn/fcn_r18-d8_4xb2-80k_deepglobe-512x1024.py b/configs/fcn/fcn_r18-d8_4xb2-80k_deepglobe-512x1024.py
@@ -0,0 +1,7 @@
+_base_ = [
+    '../_base_/models/fcn_r50-d8deepglobe.py', '../_base_/datasets/deepGlobe.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
+crop_size = (256, 256)
+data_preprocessor = dict(size=crop_size)
+model = dict(data_preprocessor=data_preprocessor)
diff --git a/...et_r50-d8_4xb2-40k_cityscapes-512x1024.py → ...net_r50-d8_4xb2-40k_deepGlobe-512x1024.py b/...et_r50-d8_4xb2-40k_cityscapes-512x1024.py → ...net_r50-d8_4xb2-40k_deepGlobe-512x1024.py
@@ -1,7 +1,7 @@
 _base_ = [
-    '../_base_/models/ccnet_r50-d8.py', '../_base_/datasets/cityscapes.py',
+    '../_base_/models/gcnet_r50-d8.py', '../_base_/datasets/deepGlobe.py',
     '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
 ]
-crop_size = (512, 1024)
+crop_size = (256, 256)
 data_preprocessor = dict(size=crop_size)
 model = dict(data_preprocessor=data_preprocessor)
diff --git a/configs/hrnet/fcn_hr18_4xb2-40k_deepglobe-512x1024.py b/configs/hrnet/fcn_hr18_4xb2-40k_deepglobe-512x1024.py
@@ -0,0 +1,7 @@
+_base_ = [
+    '../_base_/models/fcn_hr18_deepGlobe.py', '../_base_/datasets/deepGlobe.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
+crop_size = (256, 256)
+data_preprocessor = dict(size=crop_size)
+model = dict(data_preprocessor=data_preprocessor)
diff --git a/configs/unet/unet-s5-d16_pspnet_4xb4-40k_deepglobe-256x256.py b/configs/unet/unet-s5-d16_pspnet_4xb4-40k_deepglobe-256x256.py
@@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/pspnet_unet_deepglobe_s5-d16.py', '../_base_/datasets/deepGlobe.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
+crop_size = (256, 256)
+data_preprocessor = dict(size=crop_size)
+model = dict(
+    data_preprocessor=data_preprocessor,
+    test_cfg=dict(crop_size=(256, 256), stride=(85, 85)))
diff --git a/docs/en/stat.py b/docs/en/stat.py
diff --git a/docs/zh_cn/stat.py b/docs/zh_cn/stat.py
diff --git a/mmseg/configs/_base_/schedules/schedule_40k.py b/mmseg/configs/_base_/schedules/schedule_40k.py
@@ -1,34 +1,25 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,
-                            LoggerHook, ParamSchedulerHook)
-from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper
-from mmengine.optim.scheduler.lr_scheduler import PolyLR
-from mmengine.runner.loops import IterBasedTrainLoop, TestLoop, ValLoop
-from torch.optim.sgd import SGD
-
-from mmseg.engine import SegVisualizationHook
-
+#configs/_base_/schedules/schedule_40k.py
 # optimizer
-optimizer = dict(type=SGD, lr=0.01, momentum=0.9, weight_decay=0.0005)
-optim_wrapper = dict(type=OptimWrapper, optimizer=optimizer, clip_grad=None)
-
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer, clip_grad=None)
+# learning policy
 param_scheduler = [
     dict(
-        type=PolyLR,
+        type='PolyLR',
         eta_min=1e-4,
         power=0.9,
         begin=0,
-        end=40000,
+        end=10000,
         by_epoch=False)
 ]
 # training schedule for 40k
-train_cfg = dict(type=IterBasedTrainLoop, max_iters=40000, val_interval=4000)
-val_cfg = dict(type=ValLoop)
-test_cfg = dict(type=TestLoop)
+train_cfg = dict(type='IterBasedTrainLoop', max_iters=10000, val_interval=1000)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
 default_hooks = dict(
-    timer=dict(type=IterTimerHook),
-    logger=dict(type=LoggerHook, interval=50, log_metric_by_epoch=False),
-    param_scheduler=dict(type=ParamSchedulerHook),
-    checkpoint=dict(type=CheckpointHook, by_epoch=False, interval=4000),
-    sampler_seed=dict(type=DistSamplerSeedHook),
-    visualization=dict(type=SegVisualizationHook))
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=1000),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
diff --git a/mmseg/datasets/__init__.py b/mmseg/datasets/__init__.py
@@ -1,3 +1,4 @@
+#mmseg/datasets/__init__.py
 # Copyright (c) OpenMMLab. All rights reserved.
 # yapf: disable
 from .ade import ADE20KDataset
@@ -26,6 +27,7 @@
 from .refuge import REFUGEDataset
 from .stare import STAREDataset
 from .synapse import SynapseDataset
+from .deepGlobe import DeepGlobeDataset
 # yapf: disable
 from .transforms import (CLAHE, AdjustGamma, Albu, BioMedical3DPad,
                          BioMedical3DRandomCrop, BioMedical3DRandomFlip,
@@ -61,5 +63,5 @@
     'MapillaryDataset_v2', 'Albu', 'LEVIRCDDataset',
     'LoadMultipleRSImageFromFile', 'LoadSingleRSImageFromFile',
     'ConcatCDInput', 'BaseCDDataset', 'DSDLSegDataset', 'BDD100KDataset',
-    'NYUDataset', 'HSIDrive20Dataset'
+    'NYUDataset', 'HSIDrive20Dataset', 'DeepGlobeDataset'
 ]
diff --git a/mmseg/datasets/deepGlobe.py b/mmseg/datasets/deepGlobe.py
@@ -0,0 +1,48 @@
+#mmseg/datasets/deepGlobe.py
+# Copyright (c) OpenMMLab. All rights reserved.
+from mmseg.registry import DATASETS
+from .basesegdataset import BaseSegDataset
+import json
+import os
+from datetime import datetime
+
+import geopandas as gpd
+import numpy as np
+import pandas as pd
+import torch
+import torch.utils.data as tdata
+
+@DATASETS.register_module()
+class DeepGlobeDataset(BaseSegDataset):
+    """Deep Globe Dataset.
+
+    The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is
+    fixed to '_t.png' for Cityscapes dataset.
+    """
+    METAINFO = dict(
+        classes=('Urban', 'Agriculture', 'Range', 'Forest', 'Water', 'Barren',
+                 'Unknown'),
+        palette=[[0,255,255], [255,255,0], [255,0,255], [0,255,0],
+                 [0,0,255], [255,255,255], [1,1,1]
+                 ])
+
+    class_dict={
+                "1": "Urban",
+                "2": "Agriculture",
+                "3": "Range",
+                "4": "Forest",
+                "5": "Water",
+                "6": "Barren",
+                "7": "Unknown"
+                }
+    color_map = [
+            [0,255,255], [255,255,0], [255,0,255], [0,255,0],
+            [0,0,255], [255,255,255], [1,1,1]
+            ]
+
+    def __init__(self,
+                 img_suffix='_sat.jpg',
+                 seg_map_suffix='_mask.png',
+                 **kwargs) -> None:
+        super().__init__(
+            img_suffix=img_suffix, seg_map_suffix=seg_map_suffix, **kwargs)
diff --git a/mmseg/utils/__init__.py b/mmseg/utils/__init__.py
@@ -2,7 +2,7 @@
 # yapf: disable
 from .class_names import (ade_classes, ade_palette, bdd100k_classes,
                           bdd100k_palette, cityscapes_classes,
-                          cityscapes_palette, cocostuff_classes,
+                          cityscapes_palette, deepGlobe_classes, deepGlobe_palette, cocostuff_classes,
                           cocostuff_palette, dataset_aliases, get_classes,
                           get_palette, isaid_classes, isaid_palette,
                           loveda_classes, loveda_palette, potsdam_classes,

diff --git a/mmseg/utils/class_names.py b/mmseg/utils/class_names.py
@@ -463,6 +463,12 @@ def bdd100k_classes():
         'bicycle'
     ]
 
+def deepGlobe_classes():
+    return[
+        'Urban', 'Agriculture', 'Range', 'Forest', 'Water', 'Barren',
+        'Unknown'
+    ]
+
 
 def bdd100k_palette():
     """bdd100k palette for external use(same with cityscapes)"""
@@ -487,9 +493,15 @@ def hsidrive_palette():
             [0, 0, 255], [102, 51, 0], [255, 255, 0], [0, 207, 250],
             [255, 166, 0], [0, 204, 204]]
 
+def deepGlobe_palette():
+    """DeepGlobe palette for external use."""
+    return [[0,255,255], [255,255,0], [255,0,255], [0,255,0],
+            [0,0,255], [255,255,255], [1,1,1]]
+
 
 dataset_aliases = {
     'cityscapes': ['cityscapes'],
+    'deepGlobe': ['deepGlobe'],
     'ade': ['ade', 'ade20k'],
     'voc': ['voc', 'pascal_voc', 'voc12', 'voc12aug'],
     'pcontext': ['pcontext', 'pascal_context', 'voc2010'],

diff --git a/projects/medical/2d_image/dermoscopy/isic2016_task1/tools/prepare_dataset.py b/projects/medical/2d_image/dermoscopy/isic2016_task1/tools/prepare_dataset.py
diff --git a/projects/medical/2d_image/dermoscopy/isic2017_task1/tools/prepare_dataset.py b/projects/medical/2d_image/dermoscopy/isic2017_task1/tools/prepare_dataset.py
diff --git a/...scein_angriogram/vampire/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_vampire-512x512.py b/...scein_angriogram/vampire/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_vampire-512x512.py
diff --git a/...escein_angriogram/vampire/configs/fcn-unet-s5-d16_unet_1xb16-0.001-20k_vampire-512x512.py b/...escein_angriogram/vampire/configs/fcn-unet-s5-d16_unet_1xb16-0.001-20k_vampire-512x512.py
diff --git a/...rescein_angriogram/vampire/configs/fcn-unet-s5-d16_unet_1xb16-0.01-20k_vampire-512x512.py b/...rescein_angriogram/vampire/configs/fcn-unet-s5-d16_unet_1xb16-0.01-20k_vampire-512x512.py
diff --git a/projects/medical/2d_image/fluorescein_angriogram/vampire/configs/vampire_512x512.py b/projects/medical/2d_image/fluorescein_angriogram/vampire/configs/vampire_512x512.py
diff --git a/projects/medical/2d_image/fluorescein_angriogram/vampire/datasets/__init__.py b/projects/medical/2d_image/fluorescein_angriogram/vampire/datasets/__init__.py
diff --git a/projects/medical/2d_image/fluorescein_angriogram/vampire/datasets/vampire_dataset.py b/projects/medical/2d_image/fluorescein_angriogram/vampire/datasets/vampire_dataset.py
diff --git a/projects/medical/2d_image/fundus_photography/dr_hagis/tools/prepare_dataset.py b/projects/medical/2d_image/fundus_photography/dr_hagis/tools/prepare_dataset.py
diff --git a/projects/medical/2d_image/fundus_photography/orvs/tools/prepare_dataset.py b/projects/medical/2d_image/fundus_photography/orvs/tools/prepare_dataset.py
diff --git a/projects/medical/2d_image/histopathology/breast_cancer_cell_seg/tools/prepare_dataset.py b/projects/medical/2d_image/histopathology/breast_cancer_cell_seg/tools/prepare_dataset.py
diff --git a/projects/medical/2d_image/histopathology/conic2022_seg/tools/prepare_dataset.py b/projects/medical/2d_image/histopathology/conic2022_seg/tools/prepare_dataset.py
diff --git a/projects/medical/2d_image/histopathology/consep/tools/prepare_dataset.py b/projects/medical/2d_image/histopathology/consep/tools/prepare_dataset.py
diff --git a/..._reflectance_imaging/ravir/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_ravir-512x512.py b/..._reflectance_imaging/ravir/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_ravir-512x512.py
diff --git a/...d_reflectance_imaging/ravir/configs/fcn-unet-s5-d16_unet_1xb16-0.001-20k_ravir-512x512.py b/...d_reflectance_imaging/ravir/configs/fcn-unet-s5-d16_unet_1xb16-0.001-20k_ravir-512x512.py
diff --git a/...ed_reflectance_imaging/ravir/configs/fcn-unet-s5-d16_unet_1xb16-0.01-20k_ravir-512x512.py b/...ed_reflectance_imaging/ravir/configs/fcn-unet-s5-d16_unet_1xb16-0.01-20k_ravir-512x512.py
diff --git a/projects/medical/2d_image/infrared_reflectance_imaging/ravir/configs/ravir_512x512.py b/projects/medical/2d_image/infrared_reflectance_imaging/ravir/configs/ravir_512x512.py
diff --git a/projects/medical/2d_image/infrared_reflectance_imaging/ravir/datasets/__init__.py b/projects/medical/2d_image/infrared_reflectance_imaging/ravir/datasets/__init__.py
diff --git a/projects/medical/2d_image/infrared_reflectance_imaging/ravir/datasets/ravir_dataset.py b/projects/medical/2d_image/infrared_reflectance_imaging/ravir/datasets/ravir_dataset.py
diff --git a/projects/medical/2d_image/microscopy_images/bactteria_detection/tools/prepare_dataset.py b/projects/medical/2d_image/microscopy_images/bactteria_detection/tools/prepare_dataset.py
diff --git a/projects/medical/2d_image/x_ray/chest_image_pneum/tools/prepare_dataset.py b/projects/medical/2d_image/x_ray/chest_image_pneum/tools/prepare_dataset.py
diff --git a/setup.py b/setup.py
diff --git a/tests/data/biomedical.nii.gz b/tests/data/biomedical.nii.gz
diff --git a/tests/data/biomedical_ann.nii.gz b/tests/data/biomedical_ann.nii.gz
diff --git a/tests/data/dataset.json b/tests/data/dataset.json
diff --git a/tests/data/dsdl_seg/config.py b/tests/data/dsdl_seg/config.py
diff --git a/tests/data/dsdl_seg/defs/class-dom.yaml b/tests/data/dsdl_seg/defs/class-dom.yaml
diff --git a/tests/data/dsdl_seg/defs/segmentation-def.yaml b/tests/data/dsdl_seg/defs/segmentation-def.yaml
diff --git a/tests/data/dsdl_seg/set-train/train.yaml b/tests/data/dsdl_seg/set-train/train.yaml
diff --git a/tests/data/dsdl_seg/set-train/train_samples.json b/tests/data/dsdl_seg/set-train/train_samples.json
diff --git a/tools/dist_test.sh b/tools/dist_test.sh
diff --git a/tools/dist_train.sh b/tools/dist_train.sh
diff --git a/tools/model_test.py b/tools/model_test.py
@@ -0,0 +1,78 @@
+
+
+import os
+import mmcv
+import numpy as np
+import cv2
+from mmseg.apis import init_model, inference_model
+
+# Configuration and checkpoint paths
+CONFIG_FILE = '/Users/octaviofenollosa/GithubWeb/AIDeep/mmsegmentationEQ2/configs/hrnet/fcn_hr18_4xb2-40k_deepglobe-512x1024.py'
+CHECKPOINT_FILE = '/Users/octaviofenollosa/GithubWeb/AIDeep/mmsegmentationEQ2/work-dir/HRNet/iter_10000.pth'
+DEVICE = 'cpu'
+
+
+
+# Custom color palette
+PALETTE = np.array([
+    [0, 255, 255], 
+    [255, 255, 0], 
+    [255, 0, 255], 
+    [0, 255, 0], 
+    [0, 0, 255], 
+    [255, 255, 255], 
+    [0, 0, 0]
+], dtype=np.uint8)
+
+# Directories
+IMAGE_DIR = '/Users/octaviofenollosa/GithubWeb/AIDeep/mmsegmentationEQ2/Test_model'
+OUTPUT_DIR = '/Users/octaviofenollosa/GithubWeb/AIDeep/mmsegmentationEQ2/PrediccionesHRNet'
+
+def initialize_model(config_path, checkpoint_path, device):
+    """Initialize the segmentation model."""
+    return init_model(config_path, checkpoint_path, device=device)
+
+def create_output_directory(directory):
+    """Create the output directory if it doesn't exist."""
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+
+def get_image_paths(directory):
+    """Retrieve all image paths from the directory."""
+    return [os.path.join(directory, img_name) for img_name in os.listdir(directory)]
+
+def postprocess_mask(mask):
+    """Post-process the predicted mask."""
+    # Apply morphological operations to refine the mask
+    kernel = np.ones((3, 3), np.uint8)
+    refined_mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel)
+    return refined_mask
+
+def process_image(model, img_path):
+    """Run inference on a single image and return the color mask."""
+    result = inference_model(model, img_path)
+    mask = result.pred_sem_seg.data.cpu().numpy().astype(np.uint8).squeeze(0)
+    mask = postprocess_mask(mask)
+    return PALETTE[mask]
+
+def save_color_mask(color_mask, output_path):
+    """Save the color mask to the specified path."""
+    mmcv.imwrite(color_mask, output_path)
+
+def main():
+    """Main function to run the segmentation inference."""
+    model = initialize_model(CONFIG_FILE, CHECKPOINT_FILE, DEVICE)
+    create_output_directory(OUTPUT_DIR)
+
+    for img_path in get_image_paths(IMAGE_DIR):
+        color_mask = process_image(model, img_path)
+        if color_mask.size > 0:
+            output_path = os.path.join(OUTPUT_DIR, os.path.basename(img_path))
+            save_color_mask(color_mask, output_path)
+        else:
+            print(f"Skipping {img_path} due to invalid mask")
+
+    print(f"Inference completed. Results saved to: {OUTPUT_DIR}")
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/slurm_test.sh b/tools/slurm_test.sh
diff --git a/tools/slurm_train.sh b/tools/slurm_train.sh
diff --git a/work-dir/CCNET/20240605_012655/vis_data/20240605_012655.json b/work-dir/CCNET/20240605_012655/vis_data/20240605_012655.json
diff --git a/work-dir/CCNET/20240605_012655/vis_data/config.py b/work-dir/CCNET/20240605_012655/vis_data/config.py
@@ -0,0 +1,294 @@
+crop_size = (
+    256,
+    256,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        0.4082,
+        0.3791,
+        0.2815,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        256,
+    ),
+    std=[
+        0.1451,
+        0.1116,
+        0.1013,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'data/deepglobe_ds/'
+dataset_type = 'DeepGlobeDataset'
+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 = 'none'
+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='SyncBN'),
+        num_classes=7,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        contract_dilation=True,
+        depth=50,
+        dilations=(
+            1,
+            1,
+            2,
+            4,
+        ),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        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=[
+            0.4082,
+            0.3791,
+            0.2815,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            256,
+        ),
+        std=[
+            0.1451,
+            0.1116,
+            0.1013,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        channels=512,
+        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='SyncBN'),
+        num_classes=7,
+        recurrence=2,
+        type='CCHead'),
+    pretrained='open-mmlab://resnet50_v1c',
+    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=10000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=10000, type='IterBasedTrainLoop', val_interval=500)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train_sat',
+            seg_map_path='ann_dir/train_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    512,
+                    512,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    256,
+                    256,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    num_workers=4,
+    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=(
+            512,
+            512,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        256,
+        256,
+    ), 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=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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(type='TensorboardVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+        dict(type='TensorboardVisBackend'),
+    ])
+work_dir = '/content/drive/MyDrive/Equipo2AI/CCNET'
diff --git a/work-dir/CCNET/20240605_012655/vis_data/events.out.tfevents.1717550820.5a3f7f311a9c.4654.0 b/work-dir/CCNET/20240605_012655/vis_data/events.out.tfevents.1717550820.5a3f7f311a9c.4654.0
diff --git a/work-dir/CCNET/20240605_012655/vis_data/scalars.json b/work-dir/CCNET/20240605_012655/vis_data/scalars.json
diff --git a/work-dir/CCNET/ccnet_r50-d8_4xb2-40k_deepglobe-256x256.py b/work-dir/CCNET/ccnet_r50-d8_4xb2-40k_deepglobe-256x256.py
@@ -0,0 +1,294 @@
+crop_size = (
+    256,
+    256,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        0.4082,
+        0.3791,
+        0.2815,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        256,
+    ),
+    std=[
+        0.1451,
+        0.1116,
+        0.1013,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'data/deepglobe_ds/'
+dataset_type = 'DeepGlobeDataset'
+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 = 'none'
+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='SyncBN'),
+        num_classes=7,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        contract_dilation=True,
+        depth=50,
+        dilations=(
+            1,
+            1,
+            2,
+            4,
+        ),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        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=[
+            0.4082,
+            0.3791,
+            0.2815,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            256,
+        ),
+        std=[
+            0.1451,
+            0.1116,
+            0.1013,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        channels=512,
+        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='SyncBN'),
+        num_classes=7,
+        recurrence=2,
+        type='CCHead'),
+    pretrained='open-mmlab://resnet50_v1c',
+    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=10000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=10000, type='IterBasedTrainLoop', val_interval=500)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train_sat',
+            seg_map_path='ann_dir/train_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    512,
+                    512,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    256,
+                    256,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    num_workers=4,
+    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=(
+            512,
+            512,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        256,
+        256,
+    ), 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=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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(type='TensorboardVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+        dict(type='TensorboardVisBackend'),
+    ])
+work_dir = '/content/drive/MyDrive/Equipo2AI/CCNET'
diff --git a/work-dir/DeepLab/20240605_012836/vis_data/20240605_012836.json b/work-dir/DeepLab/20240605_012836/vis_data/20240605_012836.json
diff --git a/work-dir/DeepLab/20240605_012836/vis_data/config.py b/work-dir/DeepLab/20240605_012836/vis_data/config.py
@@ -0,0 +1,299 @@
+crop_size = (
+    256,
+    256,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        0.4082,
+        0.3791,
+        0.2815,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        256,
+    ),
+    std=[
+        0.1351,
+        0.1022,
+        0.0931,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'data/deepglobe_ds/'
+dataset_type = 'DeepGlobeDataset'
+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 = 'none'
+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='SyncBN'),
+        num_classes=7,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        contract_dilation=True,
+        depth=50,
+        dilations=(
+            1,
+            1,
+            2,
+            4,
+        ),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        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=[
+            0.4082,
+            0.3791,
+            0.2815,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            256,
+        ),
+        std=[
+            0.1351,
+            0.1022,
+            0.0931,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        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='SyncBN'),
+        num_classes=7,
+        type='ASPPHead'),
+    pretrained='open-mmlab://resnet50_v1c',
+    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=10000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=10000, type='IterBasedTrainLoop', val_interval=1000)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train_sat',
+            seg_map_path='ann_dir/train_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    512,
+                    512,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    256,
+                    256,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    num_workers=4,
+    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=(
+            512,
+            512,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        256,
+        256,
+    ), 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=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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(type='TensorboardVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+        dict(type='TensorboardVisBackend'),
+    ])
+work_dir = '/content/drive/MyDrive/Equipo2AI/work-dir/DeepLab'
diff --git a/work-dir/DeepLab/20240605_012836/vis_data/events.out.tfevents.1717550921.b21fe9e26d69.3431.0 b/work-dir/DeepLab/20240605_012836/vis_data/events.out.tfevents.1717550921.b21fe9e26d69.3431.0
diff --git a/work-dir/DeepLab/20240605_012836/vis_data/scalars.json b/work-dir/DeepLab/20240605_012836/vis_data/scalars.json
diff --git a/work-dir/DeepLab/deeplabv3_r50-d8_4xb2-40k_deepglobe-512x1024.py b/work-dir/DeepLab/deeplabv3_r50-d8_4xb2-40k_deepglobe-512x1024.py
@@ -0,0 +1,299 @@
+crop_size = (
+    256,
+    256,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        0.4082,
+        0.3791,
+        0.2815,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        256,
+    ),
+    std=[
+        0.1351,
+        0.1022,
+        0.0931,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'data/deepglobe_ds/'
+dataset_type = 'DeepGlobeDataset'
+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 = 'none'
+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='SyncBN'),
+        num_classes=7,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        contract_dilation=True,
+        depth=50,
+        dilations=(
+            1,
+            1,
+            2,
+            4,
+        ),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        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=[
+            0.4082,
+            0.3791,
+            0.2815,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            256,
+        ),
+        std=[
+            0.1351,
+            0.1022,
+            0.0931,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        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='SyncBN'),
+        num_classes=7,
+        type='ASPPHead'),
+    pretrained='open-mmlab://resnet50_v1c',
+    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=10000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=10000, type='IterBasedTrainLoop', val_interval=1000)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train_sat',
+            seg_map_path='ann_dir/train_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    512,
+                    512,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    256,
+                    256,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    num_workers=4,
+    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=(
+            512,
+            512,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        256,
+        256,
+    ), 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=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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(type='TensorboardVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+        dict(type='TensorboardVisBackend'),
+    ])
+work_dir = '/content/drive/MyDrive/Equipo2AI/work-dir/DeepLab'
diff --git a/work-dir/DeepLab/last_checkpoint b/work-dir/DeepLab/last_checkpoint
@@ -0,0 +1 @@
+/content/drive/MyDrive/Equipo2AI/work-dir/DeepLab/iter_10000.pth
diff --git a/work-dir/DeepLabPlus/20240605_191501/vis_data/20240605_191501.json b/work-dir/DeepLabPlus/20240605_191501/vis_data/20240605_191501.json
diff --git a/work-dir/DeepLabPlus/20240605_191501/vis_data/config.py b/work-dir/DeepLabPlus/20240605_191501/vis_data/config.py
@@ -0,0 +1,301 @@
+crop_size = (
+    256,
+    256,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        0.4082,
+        0.3791,
+        0.2815,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        256,
+    ),
+    std=[
+        0.1451,
+        0.1116,
+        0.1013,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'data/deepglobe_ds/'
+dataset_type = 'DeepGlobeDataset'
+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 = 'none'
+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='SyncBN'),
+        num_classes=7,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        contract_dilation=True,
+        depth=50,
+        dilations=(
+            1,
+            1,
+            2,
+            4,
+        ),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        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=[
+            0.4082,
+            0.3791,
+            0.2815,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            256,
+        ),
+        std=[
+            0.1451,
+            0.1116,
+            0.1013,
+        ],
+        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='SyncBN'),
+        num_classes=7,
+        type='DepthwiseSeparableASPPHead'),
+    pretrained='open-mmlab://resnet50_v1c',
+    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=10000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=10000, type='IterBasedTrainLoop', val_interval=500)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train_sat',
+            seg_map_path='ann_dir/train_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    512,
+                    512,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    256,
+                    256,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    num_workers=4,
+    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=(
+            512,
+            512,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        256,
+        256,
+    ), 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=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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(type='TensorboardVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+        dict(type='TensorboardVisBackend'),
+    ])
+work_dir = '/content/drive/MyDrive/Equipo2AI/DeepLabPlus_2'
diff --git a/.../DeepLabPlus/20240605_191501/vis_data/events.out.tfevents.1717614906.fa2ea8b630f5.45304.0 b/.../DeepLabPlus/20240605_191501/vis_data/events.out.tfevents.1717614906.fa2ea8b630f5.45304.0
diff --git a/work-dir/DeepLabPlus/20240605_191501/vis_data/scalars.json b/work-dir/DeepLabPlus/20240605_191501/vis_data/scalars.json
diff --git a/work-dir/DeepLabPlus/deeplabv3plus_r50-d8_4xb2-40k_deepglobe-512x1024.py b/work-dir/DeepLabPlus/deeplabv3plus_r50-d8_4xb2-40k_deepglobe-512x1024.py
@@ -0,0 +1,301 @@
+crop_size = (
+    256,
+    256,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        0.4082,
+        0.3791,
+        0.2815,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        256,
+    ),
+    std=[
+        0.1451,
+        0.1116,
+        0.1013,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'data/deepglobe_ds/'
+dataset_type = 'DeepGlobeDataset'
+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 = 'none'
+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='SyncBN'),
+        num_classes=7,
+        num_convs=1,
+        type='FCNHead'),
+    backbone=dict(
+        contract_dilation=True,
+        depth=50,
+        dilations=(
+            1,
+            1,
+            2,
+            4,
+        ),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        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=[
+            0.4082,
+            0.3791,
+            0.2815,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            256,
+        ),
+        std=[
+            0.1451,
+            0.1116,
+            0.1013,
+        ],
+        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='SyncBN'),
+        num_classes=7,
+        type='DepthwiseSeparableASPPHead'),
+    pretrained='open-mmlab://resnet50_v1c',
+    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=10000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=10000, type='IterBasedTrainLoop', val_interval=500)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train_sat',
+            seg_map_path='ann_dir/train_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    512,
+                    512,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    256,
+                    256,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    num_workers=4,
+    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=(
+            512,
+            512,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        256,
+        256,
+    ), 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=8,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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(type='TensorboardVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+        dict(type='TensorboardVisBackend'),
+    ])
+work_dir = '/content/drive/MyDrive/Equipo2AI/DeepLabPlus_2'
diff --git a/work-dir/HRNet/20240605_163912/vis_data/20240605_163912.json b/work-dir/HRNet/20240605_163912/vis_data/20240605_163912.json
diff --git a/work-dir/HRNet/20240605_163912/vis_data/config.py b/work-dir/HRNet/20240605_163912/vis_data/config.py
@@ -0,0 +1,321 @@
+crop_size = (
+    256,
+    256,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        0.4082,
+        0.3791,
+        0.2815,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        256,
+    ),
+    std=[
+        0.1351,
+        0.1022,
+        0.0931,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'data/deepglobe_ds/'
+dataset_type = 'DeepGlobeDataset'
+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 = 'none'
+load_from = None
+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=(
+                    18,
+                    36,
+                ),
+                num_modules=1),
+            stage3=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                    4,
+                ),
+                num_branches=3,
+                num_channels=(
+                    18,
+                    36,
+                    72,
+                ),
+                num_modules=4),
+            stage4=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                    4,
+                    4,
+                ),
+                num_branches=4,
+                num_channels=(
+                    18,
+                    36,
+                    72,
+                    144,
+                ),
+                num_modules=3)),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        norm_eval=False,
+        type='HRNet'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            0.4082,
+            0.3791,
+            0.2815,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            256,
+        ),
+        std=[
+            0.1351,
+            0.1022,
+            0.0931,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        channels=270,
+        concat_input=False,
+        dropout_ratio=-1,
+        in_channels=[
+            18,
+            36,
+            72,
+            144,
+        ],
+        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=7,
+        num_convs=1,
+        type='FCNHead'),
+    pretrained='open-mmlab://msra/hrnetv2_w18',
+    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=10000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=16,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=10000, type='IterBasedTrainLoop', val_interval=1000)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train_sat',
+            seg_map_path='ann_dir/train_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    512,
+                    512,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    256,
+                    256,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    num_workers=4,
+    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=(
+            512,
+            512,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        256,
+        256,
+    ), 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=16,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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(type='TensorboardVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='SegLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+        dict(type='TensorboardVisBackend'),
+    ])
+work_dir = '/content/drive/MyDrive/Equipo2AI/work-dir'
diff --git a/work-dir/HRNet/20240605_163912/vis_data/events.out.tfevents.1717605557.45d53b44f403.9655.0 b/work-dir/HRNet/20240605_163912/vis_data/events.out.tfevents.1717605557.45d53b44f403.9655.0
diff --git a/work-dir/HRNet/20240605_163912/vis_data/scalars.json b/work-dir/HRNet/20240605_163912/vis_data/scalars.json
diff --git a/work-dir/HRNet/fcn_hr18_4xb2-40k_deepglobe-512x1024.py b/work-dir/HRNet/fcn_hr18_4xb2-40k_deepglobe-512x1024.py
@@ -0,0 +1,319 @@
+crop_size = (
+    256,
+    256,
+)
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[
+        0.4082,
+        0.3791,
+        0.2815,
+    ],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(
+        256,
+        256,
+    ),
+    std=[
+        0.1351,
+        0.1022,
+        0.0931,
+    ],
+    type='SegDataPreProcessor')
+data_root = 'data/deepglobe_ds/'
+dataset_type = 'DeepGlobeDataset'
+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 = 'none'
+load_from = None
+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=(
+                    18,
+                    36,
+                ),
+                num_modules=1),
+            stage3=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                    4,
+                ),
+                num_branches=3,
+                num_channels=(
+                    18,
+                    36,
+                    72,
+                ),
+                num_modules=4),
+            stage4=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                    4,
+                    4,
+                ),
+                num_branches=4,
+                num_channels=(
+                    18,
+                    36,
+                    72,
+                    144,
+                ),
+                num_modules=3)),
+        norm_cfg=dict(requires_grad=True, type='SyncBN'),
+        norm_eval=False,
+        type='HRNet'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            0.4082,
+            0.3791,
+            0.2815,
+        ],
+        pad_val=0,
+        seg_pad_val=255,
+        size=(
+            256,
+            256,
+        ),
+        std=[
+            0.1351,
+            0.1022,
+            0.0931,
+        ],
+        type='SegDataPreProcessor'),
+    decode_head=dict(
+        align_corners=False,
+        channels=270,
+        concat_input=False,
+        dropout_ratio=-1,
+        in_channels=[
+            18,
+            36,
+            72,
+            144,
+        ],
+        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=7,
+        num_convs=1,
+        type='FCNHead'),
+    pretrained='open-mmlab://msra/hrnetv2_w18',
+    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=10000,
+        eta_min=0.0001,
+        power=0.9,
+        type='PolyLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=16,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs'),
+]
+train_cfg = dict(max_iters=10000, type='IterBasedTrainLoop', val_interval=1000)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/train_sat',
+            seg_map_path='ann_dir/train_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                keep_ratio=True,
+                ratio_range=(
+                    0.5,
+                    2.0,
+                ),
+                scale=(
+                    512,
+                    512,
+                ),
+                type='RandomResize'),
+            dict(
+                cat_max_ratio=0.75, crop_size=(
+                    256,
+                    256,
+                ), type='RandomCrop'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    num_workers=4,
+    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=(
+            512,
+            512,
+        ),
+        type='RandomResize'),
+    dict(cat_max_ratio=0.75, crop_size=(
+        256,
+        256,
+    ), 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=16,
+    dataset=dict(
+        data_prefix=dict(
+            img_path='img_dir/val_sat',
+            seg_map_path='ann_dir/val_mask_grayscale'),
+        data_root='data/deepglobe_ds/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs'),
+        ],
+        type='DeepGlobeDataset'),
+    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 = '/content/drive/MyDrive/Equipo2AI/work-dir'
diff --git a/work-dir/HRNet/last_checkpoint b/work-dir/HRNet/last_checkpoint
@@ -0,0 +1 @@
+/content/drive/MyDrive/Equipo2AI/work-dir/iter_10000.pth
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		/content/drive/MyDrive/Equipo2AI/work-dir/DeepLab/iter_10000.pth