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/double_heads/dh_faster_rcnn_r50_fpn_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/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x.py

@@ -106,6 +106,31 @@ 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,
@@ -113,35 +138,17 @@ 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/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_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/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x.py

@@ -106,6 +106,31 @@ 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,
@@ -113,35 +138,17 @@ 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/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_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/fast_mask_rcnn_r101_fpn_1x.py

@@ -74,45 +74,56 @@ 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, 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', 'proposals', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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,
         proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
-        flip_ratio=0.5,
-        with_mask=True,
-        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 + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        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 + '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/fast_mask_rcnn_r50_caffe_c4_1x.py

@@ -73,45 +73,56 @@ 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=2000),
+    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', 'proposals', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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=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,
         proposal_file=data_root + 'proposals/rpn_r50_c4_1x_train2017.pkl',
-        flip_ratio=0.5,
-        with_mask=True,
-        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,
         proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
-        flip_ratio=0,
-        with_mask=True,
-        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,
         proposal_file=data_root + 'proposals/rpn_r50_c4_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=0.01, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/fast_mask_rcnn_r50_fpn_1x.py

@@ -74,45 +74,56 @@ 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, 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', 'proposals', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+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,
         proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
-        flip_ratio=0.5,
-        with_mask=True,
-        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 + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=True,
-        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 + '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/fast_rcnn_r101_fpn_1x.py

@@ -30,11 +30,8 @@ model = dict(
         target_stds=[0.1, 0.1, 0.2, 0.2],
         reg_class_agnostic=False,
         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)))
 # model training and testing settings
 train_cfg = dict(
     rcnn=dict(
@@ -60,45 +57,54 @@ 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=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 + '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 + '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 + '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/fast_rcnn_r50_caffe_c4_1x.py

@@ -38,11 +38,8 @@ model = dict(
         target_stds=[0.1, 0.1, 0.2, 0.2],
         reg_class_agnostic=False,
         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)))
 # model training and testing settings
 train_cfg = dict(
     rcnn=dict(
@@ -68,45 +65,54 @@ 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=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=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,
         proposal_file=data_root + 'proposals/rpn_r50_c4_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,
         proposal_file=data_root + 'proposals/rpn_r50_c4_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,
         proposal_file=data_root + 'proposals/rpn_r50_c4_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=0.01, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/fast_rcnn_r50_fpn_1x.py

@@ -30,11 +30,8 @@ model = dict(
         target_stds=[0.1, 0.1, 0.2, 0.2],
         reg_class_agnostic=False,
         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)))
 # model training and testing settings
 train_cfg = dict(
     rcnn=dict(
@@ -60,45 +57,54 @@ 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=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 + '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 + '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 + '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/faster_rcnn_ohem_r50_fpn_1x.py

@@ -102,6 +102,31 @@ 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,
@@ -109,35 +134,17 @@ 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/faster_rcnn_r101_fpn_1x.py

@@ -102,6 +102,31 @@ 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,
@@ -109,35 +134,17 @@ 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/faster_rcnn_r50_caffe_c4_1x.py

@@ -107,42 +107,49 @@ 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),
+    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=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=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=0.01, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/faster_rcnn_r50_fpn_1x.py

@@ -102,6 +102,31 @@ 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,
@@ -109,35 +134,17 @@ 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/faster_rcnn_x101_32x4d_fpn_1x.py

@@ -104,6 +104,31 @@ 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,
@@ -111,35 +136,17 @@ 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/faster_rcnn_x101_64x4d_fpn_1x.py

@@ -104,6 +104,31 @@ 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,
@@ -111,35 +136,17 @@ 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/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu.py

@@ -57,6 +57,35 @@ 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, 640), (1333, 800)],
+        multiscale_mode='value',
+        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=4,
     workers_per_gpu=4,
@@ -64,37 +93,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=[(1333, 640), (1333, 800)],
-        multiscale_mode='value',
-        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',

configs/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x.py

@@ -58,6 +58,35 @@ 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),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 640), (1333, 800)],
+        multiscale_mode='value',
+        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,
@@ -65,37 +94,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=[(1333, 640), (1333, 800)],
-        multiscale_mode='value',
-        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',

configs/fcos/fcos_r50_caffe_fpn_gn_1x_4gpu.py

@@ -57,6 +57,31 @@ 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=4,
     workers_per_gpu=4,
@@ -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',