Merge branch 'develop' into feature/shh_train

.gitignore

@@ -11,4 +11,7 @@ __pycache__/
 mmsegmentation/work_dirs
 mmsegmentation/out
 mmsegmentation/wandb
-*.jpg
+*.jpg
+mmsegmentation/output
+mmsegmentation/nohup.out
+

mmsegmentation/configs/_ljh_/_base_/default_runtime.py

@@ -12,5 +12,5 @@
 log_level = 'INFO'
 load_from = None
 resume_from = None
-workflow = [('train', 1)]
+workflow = [('train', 1),('val',1)]
 cudnn_benchmark = True

mmsegmentation/configs/_ljh_/_base_/models/psanet_r50-d8.py

@@ -0,0 +1,49 @@
+# 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='PSAHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        mask_size=(97, 97),
+        psa_type='bi-direction',
+        compact=False,
+        shrink_factor=2,
+        normalization_factor=1.0,
+        psa_softmax=True,
+        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/_ljh_/_base_/schedules/schedule_160k.py

@@ -1,8 +1,11 @@
 # optimizer
-optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0005)
+# optimizer = dict(type='AdamW', lr=0.001, betas=(0.9, 0.999), weight_decay=0.0005)
 optimizer_config = dict()
+
 # learning policy
-lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-5, by_epoch=False)
+
 # runtime settings
 runner = dict(type='IterBasedRunner', max_iters=160000)
 checkpoint_config = dict(by_epoch=False, interval=16000)

mmsegmentation/configs/_ljh_/psanet_r101-d8_160k_pascal.py

@@ -0,0 +1,2 @@
+_base_ = './psanet_r50-d8_160k_pascal.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

mmsegmentation/configs/_ljh_/psanet_r50-d8_160k_pascal.py

@@ -0,0 +1,9 @@
+_base_ = [
+    './_base_/models/psanet_r50-d8.py',
+    './_base_/datasets/pascal_context.py', './_base_/default_runtime.py',
+    './_base_/schedules/schedule_160k.py'
+]
+model = dict(
+    decode_head=dict(align_corners=True),
+    auxiliary_head=dict(align_corners=True),
+    test_cfg=dict(mode='slide', crop_size=(769, 769), stride=(513, 513)))

mmsegmentation/configs/_owj_/_base_/datasets/pascal_context.py

@@ -0,0 +1,60 @@
+# dataset settings
+dataset_type = 'PascalContextDataset'
+data_root = '../data/mmseg'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+img_scale = (520, 520)
+crop_size = (480, 480)
+
+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],
+        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=4,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images',
+        ann_dir='labels',
+        split='splits/train.txt',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images',
+        ann_dir='labels',
+        split='splits/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images',
+        ann_dir='labels',
+        split='splits/test.txt',
+        pipeline=test_pipeline))

mmsegmentation/configs/_owj_/_base_/default_runtime.py

@@ -0,0 +1,16 @@
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type="TextLoggerHook", by_epoch=False),
+        dict(type="WandbLoggerHook", init_kwargs=dict(entity='cv04',project="Semantic Segmentation", name="ccnet_test")),
+    ],
+)
+
+# yapf:enable
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True

mmsegmentation/configs/_owj_/_base_/models/ccnet_r50-d8.py

@@ -0,0 +1,44 @@
+# 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='CCHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        recurrence=2,
+        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/_owj_/_base_/models/ocrnet_hr18.py

@@ -0,0 +1,68 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='CascadeEncoderDecoder',
+    num_stages=2,
+    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],
+            channels=sum([18, 36, 72, 144]),
+            in_index=(0, 1, 2, 3),
+            input_transform='resize_concat',
+            kernel_size=1,
+            num_convs=1,
+            concat_input=False,
+            dropout_ratio=-1,
+            num_classes=19,
+            norm_cfg=norm_cfg,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+        dict(
+            type='OCRHead',
+            in_channels=[18, 36, 72, 144],
+            in_index=(0, 1, 2, 3),
+            input_transform='resize_concat',
+            channels=512,
+            ocr_channels=256,
+            dropout_ratio=-1,
+            num_classes=19,
+            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'))

mmsegmentation/configs/_owj_/_base_/schedules/custom_schedule.py

@@ -0,0 +1,18 @@
+# optimizer
+optimizer = dict(type='AdamW', lr=0.00006, betas=(0.9, 0.999), weight_decay=0.01,
+                #  paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.),
+                #                                  'relative_position_bias_table': dict(decay_mult=0.),
+                #                                  'norm': dict(decay_mult=0.)})
+                                                 )
+optimizer_config = dict()
+
+lr_config = dict(policy='poly',
+                 warmup='linear',
+                 warmup_iters=1500,
+                 warmup_ratio=1e-6,
+                 power=1.0, min_lr=0.0, by_epoch=False)
+
+# runtime settings
+runner = dict(type='IterBasedRunner', max_iters=320000)
+checkpoint_config = dict(by_epoch=False, interval=32000)
+evaluation = dict(interval=32000, metric='mIoU')

mmsegmentation/configs/_owj_/_base_/schedules/schedule_160k.py

@@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+runner = dict(type='IterBasedRunner', max_iters=160000)
+checkpoint_config = dict(by_epoch=False, interval=16000)
+evaluation = dict(interval=16000, metric='mIoU', pre_eval=True)

mmsegmentation/configs/_owj_/_base_/schedules/schedule_20k.py

@@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+runner = dict(type='IterBasedRunner', max_iters=20000)
+checkpoint_config = dict(by_epoch=False, interval=2000)
+evaluation = dict(interval=2000, metric='mIoU', pre_eval=True)

mmsegmentation/configs/_owj_/_base_/schedules/schedule_320k.py

@@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+runner = dict(type='IterBasedRunner', max_iters=320000)
+checkpoint_config = dict(by_epoch=False, interval=32000)
+evaluation = dict(interval=32000, metric='mIoU')

mmsegmentation/configs/_owj_/_base_/schedules/schedule_40k.py

@@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='AdamW', lr=0.001, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+runner = dict(type='IterBasedRunner', max_iters=40000)
+checkpoint_config = dict(by_epoch=False, interval=4000)
+evaluation = dict(interval=4000, metric='mIoU', pre_eval=True)

mmsegmentation/configs/_owj_/_base_/schedules/schedule_80k.py

@@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+runner = dict(type='IterBasedRunner', max_iters=80000)
+checkpoint_config = dict(by_epoch=False, interval=8000)
+evaluation = dict(interval=8000, metric='mIoU', pre_eval=True)

mmsegmentation/configs/_owj_/ccnet_r101-d8_512x1024_40k_cityscapes.py

@@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_512x1024_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

mmsegmentation/configs/_owj_/ccnet_r50-d8_512x1024_40k_cityscapes.py

@@ -0,0 +1,4 @@
+_base_ = [
+    './_base_/models/ccnet_r50-d8.py', './_base_/datasets/pascal_context.py',
+    './_base_/default_runtime.py', './_base_/schedules/custom_schedule.py'
+]

mmsegmentation/configs/_owj_/ocrnet_hr18_512x1024_40k_cityscapes.py

@@ -0,0 +1,4 @@
+_base_ = [
+    './_base_/models/ocrnet_hr18.py', './_base_/datasets/pascal_context.py',
+    './_base_/default_runtime.py', './_base_/schedules/custom_schedule.py'
+]