Modified ddrnet. Hello, I made some small modifications to ddrnet in my own experiments and later wanted to inference these models in the model hardware library (https://platform.openmmlab.com/deploee/), so I submit this PR.

.pre-commit-config.yaml

@@ -1,66 +1,10 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
 repos:
-  - repo: https://github.com/PyCQA/flake8
-    rev: 5.0.4
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
     hooks:
-      - id: flake8
-  - repo: https://github.com/zhouzaida/isort
-    rev: 5.12.1
-    hooks:
-      - id: isort
-  - repo: https://github.com/pre-commit/mirrors-yapf
-    rev: v0.32.0
-    hooks:
-      - id: yapf
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
-    hooks:
-      - id: trailing-whitespace
-      - id: check-yaml
-      - id: end-of-file-fixer
-      - id: requirements-txt-fixer
-      - id: double-quote-string-fixer
-      - id: check-merge-conflict
-      - id: fix-encoding-pragma
-        args: ["--remove"]
-      - id: mixed-line-ending
-        args: ["--fix=lf"]
-  - repo: https://github.com/executablebooks/mdformat
-    rev: 0.7.9
-    hooks:
-      - id: mdformat
-        args: ["--number"]
-        additional_dependencies:
-          - mdformat-openmmlab
-          - mdformat_frontmatter
-          - linkify-it-py
-  - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.1
-    hooks:
-      - id: codespell
-  - repo: https://github.com/myint/docformatter
-    rev: v1.3.1
-    hooks:
-      - id: docformatter
-        args: ["--in-place", "--wrap-descriptions", "79"]
-  # temporarily remove update-model-index to avoid conflict raised
-  # by depth estimator models
-  # - repo: local
-  #   hooks:
-  #     - id: update-model-index
-  #       name: update-model-index
-  #       description: Collect model information and update model-index.yml
-  #       entry: .dev_scripts/update_model_index.py
-  #       additional_dependencies: [pyyaml]
-  #       language: python
-  #       require_serial: true
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v3.0.0
-    hooks:
-      - id: pyupgrade
-        args: ["--py36-plus"]
-  - repo: https://github.com/open-mmlab/pre-commit-hooks
-    rev: v0.2.0  # Use the rev to fix revision
-    hooks:
-      - id: check-algo-readme
-      - id: check-copyright
-        args: ["mmseg", "tools", "tests", "demo"]  # the dir_to_check with expected directory to check
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files

configs/_base_/datasets/feces.py

@@ -0,0 +1,76 @@
+# dataset settings
+dataset_type = 'Feces'
+data_root = 'D:\Allcode\mmsegmentation-dev-1.x\data\data'
+img_scale = (448, 224)
+crop_size = (224, 224)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=img_scale,
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.7),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=img_scale, 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=64,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type='RepeatDataset',
+        times=40000,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            data_prefix=dict(
+                img_path='images/training',
+                seg_map_path='annotations/training'),
+            pipeline=train_pipeline)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='IoUMetric', iou_metrics=['mIoU', 'mDice', 'mFscore'])
+test_evaluator = val_evaluator

configs/ddrnet/ohem-DAPPM-cbam-lovasz-auxhead.py

@@ -0,0 +1,109 @@
+_base_ = [
+    '../_base_/datasets/feces.py',
+    '../_base_/default_runtime.py',
+]
+
+class_weight = [0.7, 0.8, 1.1, 1.2]
+
+checkpoint = '/home/panjm/hepengguang/mmlab_he/mmsegmentation-dev-1.x/checkpoints/ddrnet23-in1kpre_3rdparty-9ca29f62.pth'  # noqa
+crop_size = (224, 224)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    size=crop_size,
+    # mean=[123.675, 116.28, 103.53],
+    # std=[58.395, 57.12, 57.375],
+    mean=[0.609, 0.604, 0.578],
+    std=[0.195, 0.192, 0.202],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    backbone=dict(
+        type='DDRNet_cbam',
+        in_channels=3,
+        channels=64,
+        ppm_channels=128,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        init_cfg=None),
+    # init_cfg=dict(type='Pretrained', checkpoint=checkpoint)),
+    decode_head=dict(
+        type='DDRHead',
+        in_channels=64 * 4,
+        channels=128,
+        dropout_ratio=0.,
+        num_classes=4,
+        align_corners=False,
+        norm_cfg=norm_cfg,
+        loss_decode=[
+            dict(
+                type='LovaszLoss', class_weight=class_weight, loss_weight=1.0),
+            dict(
+                type='OhemCrossEntropy',
+                thres=0.9,
+                min_kept=131072,
+                class_weight=class_weight,
+                loss_weight=0.4),
+        ]),
+    auxiliary_head=dict(
+        type='DDRHead',
+        in_channels=64 * 4,
+        channels=128,
+        dropout_ratio=0.,
+        num_classes=4,
+        align_corners=False,
+        norm_cfg=norm_cfg,
+        loss_decode=[
+            dict(
+                type='LovaszLoss', class_weight=class_weight, loss_weight=1.0),
+            dict(
+                type='OhemCrossEntropy',
+                thres=0.9,
+                min_kept=131072,
+                class_weight=class_weight,
+                loss_weight=0.4),
+        ]),
+
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+
+# train_dataloader = dict(batch_size=6, num_workers=4)
+
+iters = 6000
+# 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)
+# learning policy
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=0.0001,
+        power=0.9,
+        begin=0,
+        end=iters,
+        by_epoch=False)
+]
+
+# training schedule for 120k
+train_cfg = dict(type='IterBasedTrainLoop', max_iters=iters, val_interval=100)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=5, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(
+        # type='CheckpointHook', by_epoch=False, interval=100, max_keep_ckpts=2, save_best='mIoU'),
+        type='CheckpointHook',
+        by_epoch=False,
+        interval=100,
+        max_keep_ckpts=2,
+        save_best='mDice'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
+
+randomness = dict(seed=304)

configs/ddrnet/ohem-DAPPM-cbam-lovasz.py

@@ -0,0 +1,93 @@
+_base_ = [
+    '../_base_/datasets/feces.py',
+    '../_base_/default_runtime.py',
+]
+
+class_weight = [0.7, 0.8, 1.1, 1.2]
+
+checkpoint = '/home/panjm/hepengguang/mmlab_he/mmsegmentation-dev-1.x/checkpoints/ddrnet23-in1kpre_3rdparty-9ca29f62.pth'  # noqa
+crop_size = (224, 224)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    size=crop_size,
+    mean=[0.609, 0.604, 0.578],
+    std=[0.195, 0.192, 0.202],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    backbone=dict(
+        type='DDRNet_cbam',
+        in_channels=3,
+        channels=64,
+        ppm_channels=128,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        init_cfg=None),
+    # init_cfg=dict(type='Pretrained', checkpoint=checkpoint)),
+    decode_head=dict(
+        type='DDRHead',
+        in_channels=64 * 4,
+        channels=128,
+        dropout_ratio=0.,
+        num_classes=4,
+        align_corners=False,
+        norm_cfg=norm_cfg,
+        loss_decode=[
+            dict(
+                type='LovaszLoss',
+                # thres=0.9,
+                # min_kept=131072,
+                class_weight=class_weight,
+                loss_weight=1.0),
+            dict(
+                type='OhemCrossEntropy',
+                thres=0.9,
+                min_kept=131072,
+                class_weight=class_weight,
+                loss_weight=0.4),
+        ]),
+
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+
+# train_dataloader = dict(batch_size=6, num_workers=4)
+
+iters = 6000
+# 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)
+# learning policy
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=0.0001,
+        power=0.9,
+        begin=0,
+        end=iters,
+        by_epoch=False)
+]
+
+# training schedule for 120k
+train_cfg = dict(type='IterBasedTrainLoop', max_iters=iters, val_interval=100)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=5, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(
+        # type='CheckpointHook', by_epoch=False, interval=100, max_keep_ckpts=2, save_best='mIoU'),
+        type='CheckpointHook',
+        by_epoch=False,
+        interval=100,
+        max_keep_ckpts=2,
+        save_best='mDice'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
+
+randomness = dict(seed=304)