Simplify _base_ config (open-mmlab#3166)

Author: xvjiarui

configs/_base_/datasets/cityscapes_instance.py

@@ -1,4 +1,5 @@
-_base_ = './cityscapes_detection.py'
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
 img_norm_cfg = dict(
     mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
 train_pipeline = [
@@ -12,5 +13,43 @@
     dict(type='DefaultFormatBundle'),
     dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
 ]
-data = dict(train=dict(dataset=dict(pipeline=train_pipeline)))
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 1024),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=1,
+    workers_per_gpu=2,
+    train=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            ann_file=data_root +
+            'annotations/instancesonly_filtered_gtFine_train.json',
+            img_prefix=data_root + 'leftImg8bit/train/',
+            pipeline=train_pipeline)),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_val.json',
+        img_prefix=data_root + 'leftImg8bit/val/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_test.json',
+        img_prefix=data_root + 'leftImg8bit/test/',
+        pipeline=test_pipeline))
 evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/coco_instance.py

@@ -1,4 +1,5 @@
-_base_ = 'coco_detection.py'
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
 img_norm_cfg = dict(
     mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
 train_pipeline = [
@@ -11,5 +12,37 @@
     dict(type='DefaultFormatBundle'),
     dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
 ]
-data = dict(train=dict(pipeline=train_pipeline))
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
 evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/coco_instance_semantic.py

@@ -1,4 +1,4 @@
-_base_ = 'coco_detection.py'
+dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
 img_norm_cfg = dict(
     mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
@@ -32,9 +32,22 @@
         ])
 ]
 data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
     train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
         seg_prefix=data_root + 'stuffthingmaps/train2017/',
         pipeline=train_pipeline),
-    val=dict(pipeline=test_pipeline),
-    test=dict(pipeline=test_pipeline))
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
 evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/schedules/schedule_20e.py

@@ -1,4 +1,11 @@
-_base_ = './schedule_1x.py'
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=None)
 # learning policy
-lr_config = dict(step=[16, 19])
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[16, 19])
 total_epochs = 20

configs/_base_/schedules/schedule_2x.py

@@ -1,4 +1,11 @@
-_base_ = './schedule_1x.py'
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=None)
 # learning policy
-lr_config = dict(step=[16, 22])
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[16, 22])
 total_epochs = 24