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/htc/htc_x101_32x4d_fpn_20e_16gpu.py

@@ -215,6 +215,35 @@ 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, with_seg=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='SegResizeFlipPadRescale', scale_factor=1 / 8),
+    dict(type='DefaultFormatBundle'),
+    dict(
+        type='Collect',
+        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            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=1,
     workers_per_gpu=1,
@@ -222,38 +251,18 @@ 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,
         seg_prefix=data_root + 'stuffthingmaps/train2017/',
-        seg_scale_factor=1 / 8,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True,
-        with_semantic_seg=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=True,
-        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/htc/htc_x101_64x4d_fpn_20e_16gpu.py

@@ -48,13 +48,8 @@ model = dict(
             target_stds=[0.1, 0.1, 0.2, 0.2],
             reg_class_agnostic=True,
             loss_cls=dict(
-                type='CrossEntropyLoss',
-                use_sigmoid=False,
-                loss_weight=1.0),
-            loss_bbox=dict(
-                type='SmoothL1Loss',
-                beta=1.0,
-                loss_weight=1.0)),
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
         dict(
             type='SharedFCBBoxHead',
             num_fcs=2,
@@ -66,13 +61,8 @@ model = dict(
             target_stds=[0.05, 0.05, 0.1, 0.1],
             reg_class_agnostic=True,
             loss_cls=dict(
-                type='CrossEntropyLoss',
-                use_sigmoid=False,
-                loss_weight=1.0),
-            loss_bbox=dict(
-                type='SmoothL1Loss',
-                beta=1.0,
-                loss_weight=1.0)),
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
         dict(
             type='SharedFCBBoxHead',
             num_fcs=2,
@@ -84,13 +74,8 @@ model = dict(
             target_stds=[0.033, 0.033, 0.067, 0.067],
             reg_class_agnostic=True,
             loss_cls=dict(
-                type='CrossEntropyLoss',
-                use_sigmoid=False,
-                loss_weight=1.0),
-            loss_bbox=dict(
-                type='SmoothL1Loss',
-                beta=1.0,
-                loss_weight=1.0))
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
     ],
     mask_roi_extractor=dict(
         type='SingleRoIExtractor',
@@ -215,6 +200,35 @@ 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, with_seg=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='SegResizeFlipPadRescale', scale_factor=1 / 8),
+    dict(type='DefaultFormatBundle'),
+    dict(
+        type='Collect',
+        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            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=1,
     workers_per_gpu=1,
@@ -222,38 +236,18 @@ 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,
         seg_prefix=data_root + 'stuffthingmaps/train2017/',
-        seg_scale_factor=1 / 8,
-        with_mask=True,
-        with_crowd=True,
-        with_label=True,
-        with_semantic_seg=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=True,
-        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/libra_rcnn/libra_fast_rcnn_r50_fpn_1x.py

@@ -75,46 +75,55 @@ 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='LoadProposals', num_max_proposals=2000),
+    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=0,
+    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,
         proposal_file=data_root +
         'libra_proposals/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,
         proposal_file=data_root + 'libra_proposals/rpn_r50_fpn_1x_val2017.pkl',
-        size_divisor=32,
-        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,
         proposal_file=data_root + 'libra_proposals/rpn_r50_fpn_1x_val2017.pkl',
-        size_divisor=32,
-        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/libra_rcnn/libra_faster_rcnn_r101_fpn_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),
+    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,
@@ -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=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/libra_rcnn/libra_faster_rcnn_r50_fpn_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),
+    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,
@@ -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=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/libra_rcnn/libra_faster_rcnn_x101_64x4d_fpn_1x.py

@@ -122,6 +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),
+    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,
@@ -129,35 +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=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/libra_rcnn/libra_retinanet_r50_fpn_1x.py

@@ -74,6 +74,31 @@ 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,
@@ -81,36 +106,17 @@ 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/mask_rcnn_r101_fpn_1x.py

@@ -116,6 +116,31 @@ 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,
@@ -123,35 +148,17 @@ 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/mask_rcnn_r50_caffe_c4_1x.py

@@ -120,42 +120,49 @@ 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=1,
+    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,
-        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=0.01, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/mask_rcnn_r50_fpn_1x.py

@@ -116,6 +116,31 @@ 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,
@@ -123,35 +148,17 @@ 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/mask_rcnn_x101_32x4d_fpn_1x.py

@@ -118,6 +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,
@@ -125,35 +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/mask_rcnn_x101_64x4d_fpn_1x.py

@@ -118,6 +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,
@@ -125,35 +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/ms_rcnn/ms_rcnn_r101_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, 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,
@@ -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=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/ms_rcnn/ms_rcnn_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, 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,
@@ -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=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/ms_rcnn/ms_rcnn_x101_64x4d_fpn_1x.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/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py

@@ -102,11 +102,36 @@ dataset_type = 'VOCDataset'
 data_root = 'data/VOCdevkit/'
 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=(1000, 600), 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=(1000, 600),
+        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,
     train=dict(
-        type='RepeatDataset',  # to avoid reloading datasets frequently
+        type='RepeatDataset',
         times=3,
         dataset=dict(
             type=dataset_type,
@@ -115,35 +140,17 @@ data = dict(
                 data_root + 'VOC2012/ImageSets/Main/trainval.txt'
             ],
             img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
-            img_scale=(1000, 600),
-            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 + 'VOC2007/ImageSets/Main/test.txt',
         img_prefix=data_root + 'VOC2007/',
-        img_scale=(1000, 600),
-        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 + 'VOC2007/ImageSets/Main/test.txt',
         img_prefix=data_root + 'VOC2007/',
-        img_scale=(1000, 600),
-        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=0.01, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/pascal_voc/ssd300_voc.py

@@ -23,6 +23,7 @@ model = dict(
         anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2], [2]),
         target_means=(.0, .0, .0, .0),
         target_stds=(0.1, 0.1, 0.2, 0.2)))
+# model training and testing settings
 cudnn_benchmark = True
 train_cfg = dict(
     assigner=dict(
@@ -42,14 +43,50 @@ test_cfg = dict(
     min_bbox_size=0,
     score_thr=0.02,
     max_per_img=200)
-# model training and testing settings
 # dataset settings
 dataset_type = 'VOCDataset'
 data_root = 'data/VOCdevkit/'
 img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile', to_float32=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PhotoMetricDistortion',
+        brightness_delta=32,
+        contrast_range=(0.5, 1.5),
+        saturation_range=(0.5, 1.5),
+        hue_delta=18),
+    dict(
+        type='Expand',
+        mean=img_norm_cfg['mean'],
+        to_rgb=img_norm_cfg['to_rgb'],
+        ratio_range=(1, 4)),
+    dict(
+        type='MinIoURandomCrop',
+        min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
+        min_crop_size=0.3),
+    dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(300, 300),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=False),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
 data = dict(
-    imgs_per_gpu=4,
-    workers_per_gpu=2,
+    imgs_per_gpu=8,
+    workers_per_gpu=3,
     train=dict(
         type='RepeatDataset',
         times=10,
@@ -60,51 +97,17 @@ data = dict(
                 data_root + 'VOC2012/ImageSets/Main/trainval.txt'
             ],
             img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
-            img_scale=(300, 300),
-            img_norm_cfg=img_norm_cfg,
-            size_divisor=None,
-            flip_ratio=0.5,
-            with_mask=False,
-            with_crowd=False,
-            with_label=True,
-            test_mode=False,
-            extra_aug=dict(
-                photo_metric_distortion=dict(
-                    brightness_delta=32,
-                    contrast_range=(0.5, 1.5),
-                    saturation_range=(0.5, 1.5),
-                    hue_delta=18),
-                expand=dict(
-                    mean=img_norm_cfg['mean'],
-                    to_rgb=img_norm_cfg['to_rgb'],
-                    ratio_range=(1, 4)),
-                random_crop=dict(
-                    min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
-            resize_keep_ratio=False)),
+            pipeline=train_pipeline)),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
         img_prefix=data_root + 'VOC2007/',
-        img_scale=(300, 300),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=None,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True,
-        resize_keep_ratio=False),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
         img_prefix=data_root + 'VOC2007/',
-        img_scale=(300, 300),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=None,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True,
-        resize_keep_ratio=False))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
 optimizer_config = dict()

configs/pascal_voc/ssd512_voc.py

@@ -23,6 +23,7 @@ model = dict(
         anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]),
         target_means=(.0, .0, .0, .0),
         target_stds=(0.1, 0.1, 0.2, 0.2)))
+# model training and testing settings
 cudnn_benchmark = True
 train_cfg = dict(
     assigner=dict(
@@ -42,14 +43,50 @@ test_cfg = dict(
     min_bbox_size=0,
     score_thr=0.02,
     max_per_img=200)
-# model training and testing settings
 # dataset settings
 dataset_type = 'VOCDataset'
 data_root = 'data/VOCdevkit/'
 img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile', to_float32=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PhotoMetricDistortion',
+        brightness_delta=32,
+        contrast_range=(0.5, 1.5),
+        saturation_range=(0.5, 1.5),
+        hue_delta=18),
+    dict(
+        type='Expand',
+        mean=img_norm_cfg['mean'],
+        to_rgb=img_norm_cfg['to_rgb'],
+        ratio_range=(1, 4)),
+    dict(
+        type='MinIoURandomCrop',
+        min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
+        min_crop_size=0.3),
+    dict(type='Resize', img_scale=(512, 512), keep_ratio=False),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(512, 512),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=False),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
 data = dict(
-    imgs_per_gpu=4,
-    workers_per_gpu=2,
+    imgs_per_gpu=8,
+    workers_per_gpu=3,
     train=dict(
         type='RepeatDataset',
         times=10,
@@ -60,51 +97,17 @@ data = dict(
                 data_root + 'VOC2012/ImageSets/Main/trainval.txt'
             ],
             img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
-            img_scale=(512, 512),
-            img_norm_cfg=img_norm_cfg,
-            size_divisor=None,
-            flip_ratio=0.5,
-            with_mask=False,
-            with_crowd=False,
-            with_label=True,
-            test_mode=False,
-            extra_aug=dict(
-                photo_metric_distortion=dict(
-                    brightness_delta=32,
-                    contrast_range=(0.5, 1.5),
-                    saturation_range=(0.5, 1.5),
-                    hue_delta=18),
-                expand=dict(
-                    mean=img_norm_cfg['mean'],
-                    to_rgb=img_norm_cfg['to_rgb'],
-                    ratio_range=(1, 4)),
-                random_crop=dict(
-                    min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
-            resize_keep_ratio=False)),
+            pipeline=train_pipeline)),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
         img_prefix=data_root + 'VOC2007/',
-        img_scale=(512, 512),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=None,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True,
-        resize_keep_ratio=False),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
         img_prefix=data_root + 'VOC2007/',
-        img_scale=(512, 512),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=None,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True,
-        resize_keep_ratio=False))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
 optimizer_config = dict()

configs/retinanet_r101_fpn_1x.py

@@ -57,6 +57,31 @@ 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,
@@ -64,36 +89,17 @@ 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/retinanet_r50_fpn_1x.py

@@ -57,6 +57,31 @@ 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,
@@ -64,36 +89,17 @@ 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))