[Fix] Fix optim wrapper configs

configs/deeplabv3/deeplabv3_r50-d8_480x480_40k_pascal_context.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/deeplabv3/deeplabv3_r50-d8_480x480_40k_pascal_context_59.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/deeplabv3/deeplabv3_r50-d8_480x480_80k_pascal_context.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/deeplabv3/deeplabv3_r50-d8_480x480_80k_pascal_context_59.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/deeplabv3plus/deeplabv3plus_r50-d8_480x480_40k_pascal_context.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/deeplabv3plus/deeplabv3plus_r50-d8_480x480_40k_pascal_context_59.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/deeplabv3plus/deeplabv3plus_r50-d8_480x480_80k_pascal_context.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/deeplabv3plus/deeplabv3plus_r50-d8_480x480_80k_pascal_context_59.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/dnlnet/dnl_r50-d8_769x769_80k_cityscapes.py

@@ -10,6 +10,7 @@ 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)))
-optimizer = dict(
+
+optim_wrapper = dict(
     paramwise_cfg=dict(
         custom_keys=dict(theta=dict(wd_mult=0.), phi=dict(wd_mult=0.))))

configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py

@@ -12,3 +12,4 @@ test_dataloader = val_dataloader
 
 # Re-config the optimizer.
 optimizer = dict(type='SGD', lr=0.12, momentum=0.9, weight_decay=4e-5)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/fcn/fcn_r50-d8_480x480_40k_pascal_context.py

@@ -10,3 +10,4 @@ model = dict(
     auxiliary_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/fcn/fcn_r50-d8_480x480_40k_pascal_context_59.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/fcn/fcn_r50-d8_480x480_80k_pascal_context.py

@@ -10,3 +10,4 @@ model = dict(
     auxiliary_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/fcn/fcn_r50-d8_480x480_80k_pascal_context_59.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/hrnet/fcn_hr18_480x480_40k_pascal_context.py

@@ -9,3 +9,4 @@ model = dict(
     decode_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/hrnet/fcn_hr18_480x480_40k_pascal_context_59.py

@@ -9,3 +9,4 @@ model = dict(
     decode_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/hrnet/fcn_hr18_480x480_80k_pascal_context.py

@@ -9,3 +9,4 @@ model = dict(
     decode_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/hrnet/fcn_hr18_480x480_80k_pascal_context_59.py

@@ -9,3 +9,4 @@ model = dict(
     decode_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/pspnet/pspnet_r50-d8_480x480_40k_pascal_context.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/pspnet/pspnet_r50-d8_480x480_40k_pascal_context_59.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/pspnet/pspnet_r50-d8_480x480_80k_pascal_context.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=60),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/pspnet/pspnet_r50-d8_480x480_80k_pascal_context_59.py

@@ -11,3 +11,4 @@ model = dict(
     auxiliary_head=dict(num_classes=59),
     test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
 optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)

configs/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k.py

@@ -7,7 +7,7 @@ crop_size = (512, 512)
 data_preprocessor = dict(size=crop_size)
 model = dict(data_preprocessor=data_preprocessor)
 optimizer = dict(lr=0.001, weight_decay=0.0)
-
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
 train_dataloader = dict(
     # num_gpus: 8 -> batch_size: 8
     batch_size=1)

configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py

@@ -25,7 +25,7 @@ model = dict(
     test_cfg=dict(mode='slide', crop_size=(640, 640), stride=(608, 608)))
 
 optimizer = dict(lr=0.001, weight_decay=0.0)
-
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
 train_dataloader = dict(
     # num_gpus: 8 -> batch_size: 8
     batch_size=1)

configs/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k.py

@@ -29,7 +29,7 @@ model = dict(
             type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)))
 
 optimizer = dict(lr=0.001, weight_decay=0.0)
-
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
 train_dataloader = dict(
     # num_gpus: 8 -> batch_size: 8
     batch_size=1)

configs/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k.py

@@ -19,7 +19,7 @@ model = dict(
         embed_dims=192))
 
 optimizer = dict(lr=0.001, weight_decay=0.0)
-
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
 train_dataloader = dict(
     # num_gpus: 8 -> batch_size: 8
     batch_size=1)

configs/setr/setr_mla_512x512_160k_b8_ade20k.py

@@ -79,11 +79,11 @@ model = dict(
     test_cfg=dict(mode='slide', crop_size=(512, 512), stride=(341, 341)),
 )
 
-optimizer = dict(
+optimizer = dict(lr=0.001, weight_decay=0.0)
-    lr=0.001,
+optim_wrapper = dict(
-    weight_decay=0.0,
+    type='OptimWrapper',
+    optimizer=optimizer,
     paramwise_cfg=dict(custom_keys={'head': dict(lr_mult=10.)}))
-
 # num_gpus: 8 -> batch_size: 8
 train_dataloader = dict(batch_size=1)
 val_dataloader = dict(batch_size=1)

configs/setr/setr_naive_512x512_160k_b16_ade20k.py

@@ -61,11 +61,11 @@ model = dict(
     test_cfg=dict(mode='slide', crop_size=(512, 512), stride=(341, 341)),
 )
 
-optimizer = dict(
+optimizer = dict(lr=0.01, weight_decay=0.0)
-    lr=0.01,
+optim_wrapper = dict(
-    weight_decay=0.0,
+    type='OptimWrapper',
+    optimizer=optimizer,
     paramwise_cfg=dict(custom_keys={'head': dict(lr_mult=10.)}))
-
 # num_gpus: 8 -> batch_size: 16
 train_dataloader = dict(batch_size=2)
 val_dataloader = dict(batch_size=1)

configs/setr/setr_pup_512x512_160k_b16_ade20k.py

@@ -61,11 +61,11 @@ model = dict(
     test_cfg=dict(mode='slide', crop_size=(512, 512), stride=(341, 341)),
 )
 
-optimizer = dict(
+optimizer = dict(lr=0.001, weight_decay=0.0)
-    lr=0.001,
+optim_wrapper = dict(
-    weight_decay=0.0,
+    type='OptimWrapper',
+    optimizer=optimizer,
     paramwise_cfg=dict(custom_keys={'head': dict(lr_mult=10.)}))
-
 # num_gpus: 8 -> batch_size: 16
 train_dataloader = dict(batch_size=2)
 val_dataloader = dict(batch_size=1)

configs/setr/setr_vit-large_mla_8x1_768x768_80k_cityscapes.py

@@ -13,9 +13,10 @@ model = dict(
             type='Pretrained', checkpoint='pretrain/vit_large_p16.pth')),
     test_cfg=dict(mode='slide', crop_size=(768, 768), stride=(512, 512)))
 
-optimizer = dict(
+optimizer = dict(lr=0.002, weight_decay=0.0)
-    lr=0.002,
+optim_wrapper = dict(
-    weight_decay=0.0,
+    type='OptimWrapper',
+    optimizer=optimizer,
     paramwise_cfg=dict(custom_keys={'head': dict(lr_mult=10.)}))
 train_dataloader = dict(batch_size=1)
 val_dataloader = dict(batch_size=1)

configs/setr/setr_vit-large_naive_8x1_768x768_80k_cityscapes.py

@@ -14,10 +14,11 @@ model = dict(
             type='Pretrained', checkpoint='pretrain/vit_large_p16.pth')),
     test_cfg=dict(mode='slide', crop_size=(768, 768), stride=(512, 512)))
 
-optimizer = dict(
+optimizer = dict(weight_decay=0.0)
-    weight_decay=0.0,
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=optimizer,
     paramwise_cfg=dict(custom_keys={'head': dict(lr_mult=10.)}))
-
 train_dataloader = dict(batch_size=1)
 val_dataloader = dict(batch_size=1)
 test_dataloader = val_dataloader

configs/setr/setr_vit-large_pup_8x1_768x768_80k_cityscapes.py

@@ -59,8 +59,10 @@ model = dict(
     ],
     test_cfg=dict(mode='slide', crop_size=crop_size, stride=(512, 512)))
 
-optimizer = dict(
+optimizer = dict(weight_decay=0.0)
-    weight_decay=0.0,
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=optimizer,
     paramwise_cfg=dict(custom_keys={'head': dict(lr_mult=10.)}))
 
 train_dataloader = dict(batch_size=1)