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/guided_anchoring/ga_faster_x101_32x4d_fpn_1x.py

@@ -127,6 +127,31 @@ 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,
@@ -134,35 +159,17 @@ data = dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_train2017.json',
         img_prefix=data_root + 'train2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0.5,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_crowd=True,
-        with_label=True),
+        pipeline=test_pipeline),
     test=dict(
         type=dataset_type,
         ann_file=data_root + 'annotations/instances_val2017.json',
         img_prefix=data_root + 'val2017/',
-        img_scale=(1333, 800),
-        img_norm_cfg=img_norm_cfg,
-        size_divisor=32,
-        flip_ratio=0,
-        with_mask=False,
-        with_label=False,
-        test_mode=True))
+        pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

configs/guided_anchoring/ga_retinanet_r50_caffe_fpn_1x.py

@@ -84,6 +84,31 @@ dataset_type = 'CocoDataset'
 data_root = 'data/coco/'
 img_norm_cfg = dict(
     mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
 data = dict(
     imgs_per_gpu=2,
     workers_per_gpu=2,
@@ -91,36 +116,17 @@ 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))