Make data pre-processing pipeline customizable (#935)

* define data pipelines

* update two config files

* minor fix for config files

* allow img_scale to be optional and update config

* add some docstrings

* add extra aug to transform

* bug fix for mask resizing

* fix cropping

* add faster rcnn example

* fix imports

* fix robustness testing

* add img_norm_cfg to img_meta

* fix the inference api with the new data pipeline

* fix proposal loading

* delete args of DefaultFormatBundle

* add more configs

* update configs

* bug fix

* add a brief doc

* update gt_labels in RandomCrop

* fix key error for new apis

* bug fix for masks of crowd bboxes

* add argument data_root

* minor fix

* update new hrnet configs

* update docs

* rename MultiscaleFlipAug to MultiScaleFlipAug

* add __repr__ for all transforms

* move DATA_PIPELINE.md to docs/

* fix image url

configs/fp16/faster_rcnn_r50_fpn_fp16_1x.py

@@ -105,6 +105,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -112,35 +137,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/fp16/mask_rcnn_r50_fpn_fp16_1x.py

@@ -119,6 +119,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -126,35 +151,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/fp16/retinanet_r50_fpn_fp16_1x.py

@@ -60,6 +60,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -67,36 +92,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=False,
-        with_crowd=False,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=False,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_1x.py

@@ -9,9 +9,7 @@ model = dict(
         out_indices=(0, 1, 2, 3),
         frozen_stages=1,
         style='pytorch',
-        gcb=dict(
-            ratio=1./16.,
-        ),
+        gcb=dict(ratio=1. / 16., ),
         stage_with_gcb=(False, True, True, True)),
     neck=dict(
         type='FPN',
@@ -120,6 +118,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -127,35 +150,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_syncbn_1x.py

@@ -11,9 +11,7 @@ model = dict(
         out_indices=(0, 1, 2, 3),
         frozen_stages=1,
         style='pytorch',
-        gcb=dict(
-            ratio=1./16.,
-        ),
+        gcb=dict(ratio=1. / 16., ),
         stage_with_gcb=(False, True, True, True),
         norm_eval=False,
         norm_cfg=norm_cfg),
@@ -124,6 +122,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -131,35 +154,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_1x.py

@@ -9,9 +9,7 @@ model = dict(
         out_indices=(0, 1, 2, 3),
         frozen_stages=1,
         style='pytorch',
-        gcb=dict(
-            ratio=1./4.,
-        ),
+        gcb=dict(ratio=1. / 4., ),
         stage_with_gcb=(False, True, True, True)),
     neck=dict(
         type='FPN',
@@ -120,6 +118,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -127,35 +150,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_syncbn_1x.py

@@ -11,9 +11,7 @@ model = dict(
         out_indices=(0, 1, 2, 3),
         frozen_stages=1,
         style='pytorch',
-        gcb=dict(
-            ratio=1./4.,
-        ),
+        gcb=dict(ratio=1. / 4., ),
         stage_with_gcb=(False, True, True, True),
         norm_eval=False,
         norm_cfg=norm_cfg),
@@ -124,6 +122,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -131,35 +154,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gcnet/mask_rcnn_r50_fpn_sbn_1x.py

@@ -120,6 +120,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -127,35 +152,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/ghm/retinanet_ghm_r50_fpn_1x.py

@@ -35,11 +35,7 @@ model = dict(
             use_sigmoid=True,
             loss_weight=1.0),
         loss_bbox=dict(
-            type='GHMR',
-            mu=0.02,
-            bins=10,
-            momentum=0.7,
-            loss_weight=10.0)))
+            type='GHMR', mu=0.02, bins=10, momentum=0.7, loss_weight=10.0)))
 # training and testing settings
 train_cfg = dict(
     assigner=dict(
@@ -62,6 +58,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -69,36 +90,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=False,
-        with_crowd=False,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=False,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py

@@ -109,6 +109,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -116,35 +141,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_20_23_24e.py

@@ -128,6 +128,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -135,35 +160,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_2x.py

@@ -128,6 +128,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -135,35 +160,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gn+ws/mask_rcnn_x101_32x4d_fpn_gn_ws_2x.py

@@ -130,6 +130,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -137,35 +162,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gn/mask_rcnn_r101_fpn_gn_2x.py

@@ -124,6 +124,31 @@ dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
 img_norm_cfg = dict(
     mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -131,35 +156,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gn/mask_rcnn_r50_fpn_gn_2x.py

@@ -124,6 +124,31 @@ dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
 img_norm_cfg = dict(
     mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -131,35 +156,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/gn/mask_rcnn_r50_fpn_gn_contrib_2x.py

@@ -124,6 +124,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -131,35 +156,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/grid_rcnn/grid_rcnn_gn_head_r50_fpn_2x.py

@@ -113,6 +113,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -120,35 +145,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=None)

configs/grid_rcnn/grid_rcnn_gn_head_x101_32x4d_fpn_2x.py

@@ -115,6 +115,31 @@ 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 = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -122,35 +147,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=None)

configs/guided_anchoring/ga_fast_r50_caffe_fpn_1x.py

@@ -59,48 +59,54 @@ dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
 img_norm_cfg = dict(
     mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadProposals', num_max_proposals=300),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadProposals', num_max_proposals=None),
+    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', 'proposals']),
+        ])
+]
 data = dict(
     imgs_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/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        num_max_proposals=300,
         proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_train2017.pkl',
-        flip_ratio=0.5,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        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/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        num_max_proposals=300,
         proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_val2017.pkl',
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        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/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        num_max_proposals=300,
         proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_val2017.pkl',
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/guided_anchoring/ga_faster_r50_caffe_fpn_1x.py

@@ -127,6 +127,31 @@ dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
 img_norm_cfg = dict(
     mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    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='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+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(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -134,35 +159,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))