[Refactor] Refactor base configs.

open-mmlab · Jul 19, 2022 · ae90d99 · ae90d99
1 parent ef1448c
commit ae90d99
Show file tree

Hide file tree

Showing 47 changed files with 744 additions and 1,015 deletions.
diff --git a/configs/_base_/datasets/coco_detection.py b/configs/_base_/datasets/coco_detection.py
@@ -1,45 +1,60 @@
 # dataset settings
 dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
 train_pipeline = [
-    dict(type='LoadImageFromFile'),
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
     dict(type='LoadAnnotations', with_bbox=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'data_sample']),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
 ]
 test_pipeline = [
-    dict(type='LoadImageFromFile'),
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
     dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1333, 800),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Pad', size_divisor=32),
-            dict(type='DefaultFormatBundle'),
-            dict(type='Collect', keys=['img', 'data_sample']),
-        ])
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
 ]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
         type=dataset_type,
-        ann_file=data_root + 'annotations/instances_train2017.json',
-        img_prefix=data_root + 'train2017/',
-        pipeline=train_pipeline),
-    val=dict(
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=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/',
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
         pipeline=test_pipeline))
-evaluation = dict(interval=1, metric='bbox')
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric='bbox')
+test_evaluator = val_evaluator
diff --git a/configs/_base_/datasets/coco_instance.py b/configs/_base_/datasets/coco_instance.py
@@ -1,45 +1,60 @@
 # dataset settings
 dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
 train_pipeline = [
-    dict(type='LoadImageFromFile'),
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
     dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'data_sample']),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
 ]
 test_pipeline = [
-    dict(type='LoadImageFromFile'),
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
     dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1333, 800),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Pad', size_divisor=32),
-            dict(type='DefaultFormatBundle'),
-            dict(type='Collect', keys=['img', 'data_sample']),
-        ])
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
 ]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
         type=dataset_type,
-        ann_file=data_root + 'annotations/instances_train2017.json',
-        img_prefix=data_root + 'train2017/',
-        pipeline=train_pipeline),
-    val=dict(
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=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/',
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
         pipeline=test_pipeline))
-evaluation = dict(metric=['bbox', 'segm'])
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric=['bbox', 'segm'])
+test_evaluator = val_evaluator
diff --git a/configs/_base_/datasets/coco_panoptic.py b/configs/_base_/datasets/coco_panoptic.py
@@ -1,53 +1,65 @@
 # dataset settings
 dataset_type = 'CocoPanopticDataset'
 data_root = 'data/coco/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
 train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='LoadPanopticAnnotations',
-        with_bbox=True,
-        with_mask=True,
-        with_seg=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Pad', size_divisor=32),
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='LoadPanopticAnnotations'),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
     dict(type='SegRescale', scale_factor=1 / 4),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'data_sample']),
+    dict(type='PackDetInputs')
 ]
 test_pipeline = [
-    dict(type='LoadImageFromFile'),
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
     dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1333, 800),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Pad', size_divisor=32),
-            dict(type='DefaultFormatBundle'),
-            dict(type='Collect', keys=['img', 'data_sample']),
-        ])
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
 ]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
         type=dataset_type,
-        ann_file=data_root + 'annotations/panoptic_train2017.json',
-        img_prefix=data_root + 'train2017/',
+        data_root=data_root,
+        ann_file='annotations/panoptic_train2017.json',
         seg_prefix=data_root + 'annotations/panoptic_train2017/',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/panoptic_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        seg_prefix=data_root + 'annotations/panoptic_val2017/',
-        pipeline=test_pipeline),
-    test=dict(
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
         type=dataset_type,
-        ann_file=data_root + 'annotations/panoptic_val2017.json',
-        img_prefix=data_root + 'val2017/',
+        data_root=data_root,
+        ann_file='annotations/panoptic_val2017.json',
         seg_prefix=data_root + 'annotations/panoptic_val2017/',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
         pipeline=test_pipeline))
-evaluation = dict(interval=1, metric=['PQ'])
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoPanopticMetric',
+    ann_file=data_root + 'annotations/panoptic_val2017.json',
+    seg_prefix=data_root + 'annotations/panoptic_val2017/',
+    metric='PQ')
+test_evaluator = val_evaluator
diff --git a/configs/_base_/default_runtime.py b/configs/_base_/default_runtime.py
@@ -1,27 +1,28 @@
-checkpoint_config = dict(interval=1)
-# yapf:disable
-log_config = dict(
-    interval=50,
-    hooks=[
-        dict(type='TextLoggerHook'),
-        # dict(type='TensorboardLoggerHook')
-    ])
-# yapf:enable
-custom_hooks = [dict(type='NumClassCheckHook')]
+default_scope = 'mmdet'
+
+default_hooks = dict(
+    optimizer=dict(type='OptimizerHook', grad_clip=None),
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', interval=1),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+)
+
+env_cfg = dict(
+    cudnn_benchmark=False,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'),
+)
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')
+
+# custom_hooks = [dict(type='DetVisualizationHook', interval=10)]
 
-dist_params = dict(backend='nccl')
 log_level = 'INFO'
 load_from = None
-resume_from = None
-workflow = [('train', 1)]
-
-# disable opencv multithreading to avoid system being overloaded
-opencv_num_threads = 0
-# set multi-process start method as `fork` to speed up the training
-mp_start_method = 'fork'
+resume = False
 
-# Default setting for scaling LR automatically
-#   - `enable` means enable scaling LR automatically
-#       or not by default.
-#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
-auto_scale_lr = dict(enable=False, base_batch_size=16)
+# TODO: support auto scaling lr
diff --git a/configs/_base_/models/cascade_mask_rcnn_r50_fpn.py b/configs/_base_/models/cascade_mask_rcnn_r50_fpn.py
@@ -1,10 +1,13 @@
 # model settings
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+preprocess_cfg = dict(
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    to_rgb=True,
+    pad_size_divisor=32)
 
 model = dict(
     type='CascadeRCNN',
-    img_norm_cfg=img_norm_cfg,
+    preprocess_cfg=preprocess_cfg,
     backbone=dict(
         type='ResNet',
         depth=50,

diff --git a/configs/_base_/models/cascade_rcnn_r50_fpn.py b/configs/_base_/models/cascade_rcnn_r50_fpn.py
@@ -1,10 +1,13 @@
 # model settings
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+preprocess_cfg = dict(
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    to_rgb=True,
+    pad_size_divisor=32)
 
 model = dict(
     type='CascadeRCNN',
-    img_norm_cfg=img_norm_cfg,
+    preprocess_cfg=preprocess_cfg,
     backbone=dict(
         type='ResNet',
         depth=50,

diff --git a/configs/_base_/models/faster_rcnn_r50_caffe_c4.py b/configs/_base_/models/faster_rcnn_r50_caffe_c4.py
@@ -1,6 +1,12 @@
 # model settings
+preprocess_cfg = dict(
+    mean=[103.530, 116.280, 123.675],
+    std=[1.0, 1.0, 1.0],
+    to_rgb=False,
+    pad_size_divisor=32)
 norm_cfg = dict(type='BN', requires_grad=False)
 model = dict(
+    preprocess_cfg=preprocess_cfg,
     type='FasterRCNN',
     backbone=dict(
         type='ResNet',