🌱 Add MMSeg base configs for trash dataset

mmsegmentation/configs/_trash_/_base_/datasets/trash.py

@@ -0,0 +1,82 @@
+# dataset settings
+dataset_type = "COCOTrashDataset"
+data_root = "/opt/ml/input/mmseg/trash"
+
+classes = (
+    "Background",
+    "General trash",
+    "Paper",
+    "Paper pack",
+    "Metal",
+    "Glass",
+    "Plastic",
+    "Styrofoam",
+    "Plastic bag",
+    "Battery",
+    "Clothing",
+)
+
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True
+)
+img_scale = (512, 512)
+# crop_size = (256, 256)
+train_pipeline = [
+    dict(type="LoadImageFromFile"),
+    dict(type="LoadAnnotations"),
+    dict(type="Resize", img_scale=img_scale, ratio_range=(0.5, 2.0)),
+    # dict(type="RandomCrop", crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type="RandomFlip", prob=0.5),
+    dict(type="PhotoMetricDistortion"),
+    dict(type="Normalize", **img_norm_cfg),
+    # dict(type="Pad", size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type="DefaultFormatBundle"),
+    dict(type="Collect", keys=["img", "gt_semantic_seg"]),
+]
+test_pipeline = [
+    dict(type="LoadImageFromFile"),
+    dict(
+        type="MultiScaleFlipAug",
+        img_scale=img_scale,
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
+        flip=False,
+        transforms=[
+            dict(type="Resize", keep_ratio=True),
+            dict(type="RandomFlip"),
+            dict(type="Normalize", **img_norm_cfg),
+            dict(type="ImageToTensor", keys=["img"]),
+            dict(type="Collect", keys=["img"]),
+        ],
+    ),
+]
+
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=8,
+    train=dict(
+        type="RepeatDataset",
+        times=40000,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            img_dir="img_dir/train",
+            ann_dir="ann_dir/train",
+            pipeline=train_pipeline,
+        ),
+    ),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir="img_dir/val",
+        ann_dir="ann_dir/val",
+        pipeline=test_pipeline,
+    ),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir="img_dir/test",
+        ann_dir="ann_dir/test",
+        pipeline=test_pipeline,
+        test_mode=True,
+    ),
+)

mmsegmentation/configs/_trash_/_base_/default_runtime.py

@@ -0,0 +1,32 @@
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type="TextLoggerHook", by_epoch=False),
+        # dict(type='MlflowLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+        dict(
+            type="MMSegWandbHook",  # "WandbLoggerHook",
+            init_kwargs={
+                "project": "Semantic Segmentation",
+                "entity": "boostcamp-ai-tech-4-cv-17",
+                # "name": "mmseg",
+            },
+            interval=10,
+            log_checkpoint=True,
+            log_checkpoint_metadata=True,
+            num_eval_images=100,
+        ),
+    ],
+)
+# yapf:enable
+
+dist_params = dict(backend="nccl")
+log_level = "INFO"
+load_from = None
+resume_from = None
+
+workflow = [("train", 1)]
+# workflow = [("train", 1), ("val", 1)]
+
+cudnn_benchmark = True

mmsegmentation/configs/_trash_/_base_/models/ann_r50-d8.py

@@ -0,0 +1,48 @@
+# model settings
+norm_cfg = dict(type="SyncBN", requires_grad=True)
+model = dict(
+    type="EncoderDecoder",
+    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="ANNHead",
+        in_channels=[1024, 2048],
+        in_index=[2, 3],
+        channels=512,
+        project_channels=256,
+        query_scales=(1,),
+        key_pool_scales=(1, 3, 6, 8),
+        dropout_ratio=0.1,
+        num_classes=19,
+        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=19,
+        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"),
+)

mmsegmentation/configs/_trash_/_base_/models/apcnet_r50-d8.py

@@ -0,0 +1,46 @@
+# model settings
+norm_cfg = dict(type="SyncBN", requires_grad=True)
+model = dict(
+    type="EncoderDecoder",
+    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="APCHead",
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        pool_scales=(1, 2, 3, 6),
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=dict(type="SyncBN", requires_grad=True),
+        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=19,
+        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"),
+)

mmsegmentation/configs/_trash_/_base_/models/bisenetv1_r18-d32.py

@@ -0,0 +1,75 @@
+# model settings
+norm_cfg = dict(type="SyncBN", requires_grad=True)
+model = dict(
+    type="EncoderDecoder",
+    backbone=dict(
+        type="BiSeNetV1",
+        in_channels=3,
+        context_channels=(128, 256, 512),
+        spatial_channels=(64, 64, 64, 128),
+        out_indices=(0, 1, 2),
+        out_channels=256,
+        backbone_cfg=dict(
+            type="ResNet",
+            in_channels=3,
+            depth=18,
+            num_stages=4,
+            out_indices=(0, 1, 2, 3),
+            dilations=(1, 1, 1, 1),
+            strides=(1, 2, 2, 2),
+            norm_cfg=norm_cfg,
+            norm_eval=False,
+            style="pytorch",
+            contract_dilation=True,
+        ),
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        init_cfg=None,
+    ),
+    decode_head=dict(
+        type="FCNHead",
+        in_channels=256,
+        in_index=0,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        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,
+            channels=64,
+            num_convs=1,
+            num_classes=19,
+            in_index=1,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type="CrossEntropyLoss", use_sigmoid=False, loss_weight=1.0
+            ),
+        ),
+        dict(
+            type="FCNHead",
+            in_channels=128,
+            channels=64,
+            num_convs=1,
+            num_classes=19,
+            in_index=2,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            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"),
+)

mmsegmentation/configs/_trash_/_base_/models/bisenetv2.py

@@ -0,0 +1,90 @@
+# model settings
+norm_cfg = dict(type="SyncBN", requires_grad=True)
+model = dict(
+    type="EncoderDecoder",
+    pretrained=None,
+    backbone=dict(
+        type="BiSeNetV2",
+        detail_channels=(64, 64, 128),
+        semantic_channels=(16, 32, 64, 128),
+        semantic_expansion_ratio=6,
+        bga_channels=128,
+        out_indices=(0, 1, 2, 3, 4),
+        init_cfg=None,
+        align_corners=False,
+    ),
+    decode_head=dict(
+        type="FCNHead",
+        in_channels=128,
+        in_index=0,
+        channels=1024,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        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=16,
+            channels=16,
+            num_convs=2,
+            num_classes=19,
+            in_index=1,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type="CrossEntropyLoss", use_sigmoid=False, loss_weight=1.0
+            ),
+        ),
+        dict(
+            type="FCNHead",
+            in_channels=32,
+            channels=64,
+            num_convs=2,
+            num_classes=19,
+            in_index=2,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type="CrossEntropyLoss", use_sigmoid=False, loss_weight=1.0
+            ),
+        ),
+        dict(
+            type="FCNHead",
+            in_channels=64,
+            channels=256,
+            num_convs=2,
+            num_classes=19,
+            in_index=3,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type="CrossEntropyLoss", use_sigmoid=False, loss_weight=1.0
+            ),
+        ),
+        dict(
+            type="FCNHead",
+            in_channels=128,
+            channels=1024,
+            num_convs=2,
+            num_classes=19,
+            in_index=4,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            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"),
+)