Octavio

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'))

tools/model_test.py

@@ -1,24 +1,32 @@
+
+
 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/anyego/Desktop/mmsegmentationEQ2/configs/fcn/fcn_r18-d8_4xb2-80k_deepglobe-512x1024.py'
-CHECKPOINT_FILE = '/Users/anyego/Desktop/mmsegmentationEQ2/workdir/fcn/iter_10000.pth'
+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, 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/anyego/Desktop/mmsegmentationEQ2/Test_model'
-OUTPUT_DIR = '/Users/anyego/Desktop/mmsegmentationEQ2/PrediccionesFCN'
+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."""

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'