Skip to content

GitLab

Unverified Commit 0d5233a3 authored by Kai Chen's avatar Kai Chen Committed by GitHub
Browse files

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
parent 7bb38af4
Hide whitespace changes
Inline Side-by-side
Showing with 584 additions and 631 deletions
configs/retinanet_x101_32x4d_fpn_1x.py
View file @ 0d5233a3
......@@ -59,6 +59,31 @@ 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,
......@@ -66,36 +91,17 @@ 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_x101_64x4d_fpn_1x.py
View file @ 0d5233a3
......@@ -59,6 +59,31 @@ 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,
......@@ -66,36 +91,17 @@ 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/rpn_r101_fpn_1x.py
View file @ 0d5233a3
......@@ -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, with_label=False),
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']),
]
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,
......@@ -64,35 +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=False),
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=False),
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)
# runner configs
......
configs/rpn_r50_caffe_c4_1x.py
View file @ 0d5233a3
......@@ -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, with_label=False),
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']),
]
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,
......@@ -64,35 +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=False),
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=False),
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)
# runner configs
......
configs/rpn_r50_fpn_1x.py
View file @ 0d5233a3
......@@ -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, with_label=False),
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']),
]
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,
......@@ -64,35 +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=False),
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=False),
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)
# runner configs
......
configs/rpn_x101_32x4d_fpn_1x.py
View file @ 0d5233a3
......@@ -59,6 +59,31 @@ 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_label=False),
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']),
]
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,
......@@ -66,35 +91,17 @@ 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=False),
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=False),
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)
# runner configs
......
configs/rpn_x101_64x4d_fpn_1x.py
View file @ 0d5233a3
......@@ -59,6 +59,31 @@ 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_label=False),
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']),
]
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,
......@@ -66,35 +91,17 @@ 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=False),
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=False),
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)
# runner configs
......
configs/scratch/scratch_faster_rcnn_r50_fpn_gn_6x.py
View file @ 0d5233a3
......@@ -107,6 +107,31 @@ 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,
......@@ -114,35 +139,17 @@ 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',
......
configs/scratch/scratch_mask_rcnn_r50_fpn_gn_6x.py
View file @ 0d5233a3
......@@ -124,6 +124,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
......@@ -131,35 +156,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=True,
with_crowd=True,
with_label=True),
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=True,
with_crowd=True,
with_label=True),
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
......
configs/ssd300_coco.py
View file @ 0d5233a3
......@@ -47,6 +47,43 @@ test_cfg = dict(
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=8,
workers_per_gpu=3,
......@@ -57,51 +94,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
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 + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
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 + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
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=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
......
configs/ssd512_coco.py
View file @ 0d5233a3
......@@ -47,6 +47,43 @@ test_cfg = dict(
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=8,
workers_per_gpu=3,
......@@ -57,51 +94,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
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 + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
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 + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
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=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
......
configs/wider_face/ssd300_wider_face.py
View file @ 0d5233a3
......@@ -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(
......@@ -42,11 +43,47 @@ test_cfg = dict(
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
# model training and testing settings
# dataset settings
dataset_type = 'WIDERFaceDataset'
data_root = 'data/WIDERFace/'
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=60,
workers_per_gpu=2,
......@@ -55,57 +92,20 @@ data = dict(
times=2,
dataset=dict(
type=dataset_type,
ann_file=[
data_root + 'train.txt',
],
img_prefix=[data_root + 'WIDER_train/'],
img_scale=(300, 300),
min_size=17, # throw away very small faces to improve training,
# because 300x300 is too low resolution to detect them
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)),
ann_file=data_root + 'train.txt',
img_prefix=data_root + 'WIDER_train/',
min_size=17,
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + '/val.txt',
ann_file=data_root + 'val.txt',
img_prefix=data_root + 'WIDER_val/',
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 + '/val.txt',
ann_file=data_root + 'val.txt',
img_prefix=data_root + 'WIDER_val/',
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()
......@@ -122,7 +122,7 @@ log_config = dict(
interval=1,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
......
docs/DATA_PIPELINE.md 0 → 100644
View file @ 0d5233a3
## Data preparation pipeline
The data preparation pipeline and the dataset is decomposed. Usually a dataset
defines how to process the annotations and a data pipeline defines all the steps to prepare a data dict.
A pipeline consists of a sequence of operations. Each operation takes a dict as input and also output a dict for the next transform.
We present a classical pipeline in the following figure. The blue blocks are pipeline operations. With the pipeline going on, each operator can add new keys (marked as green) to the result dict or update the existing keys (marked as orange).
![pipeline figure](../demo/data_pipeline.png)
The operations are categorized into data loading, pre-processing, formatting and test-time augmentation.
Here is an pipeline example for Faster R-CNN.
```python
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']),
])
]
```
For each operation, we list the related dict fields that are added/updated/removed.
### Data loading
`LoadImageFromFile`
- add: img, img_shape, ori_shape
`LoadAnnotations`
- add: gt_bboxes, gt_bboxes_ignore, gt_labels, gt_masks, gt_semantic_seg, bbox_fields, mask_fields
`LoadProposals`
- add: proposals
### Pre-processing
`Resize`
- add: scale, scale_idx, pad_shape, scale_factor, keep_ratio
- update: img, img_shape, *bbox_fields, *mask_fields
`RandomFlip`
- add: flip
- update: img, *bbox_fields, *mask_fields
`Pad`
- add: pad_fixed_size, pad_size_divisor
- update: img, pad_shape, *mask_fields
`RandomCrop`
- update: img, pad_shape, gt_bboxes, gt_labels, gt_masks, *bbox_fields
`Normalize`
- add: img_norm_cfg
- update: img
`SegResizeFlipPadRescale`
- update: gt_semantic_seg
`PhotoMetricDistortion`
- update: img
`Expand`
- update: img, gt_bboxes
`MinIoURandomCrop`
- update: img, gt_bboxes, gt_labels
`Corrupt`
- update: img
### Formatting
`ToTensor`
- update: specified by `keys`.
`ImageToTensor`
- update: specified by `keys`.
`Transpose`
- update: specified by `keys`.
`ToDataContainer`
- update: specified by `fields`.
`DefaultFormatBundle`
- update: img, proposals, gt_bboxes, gt_bboxes_ignore, gt_labels, gt_masks, gt_semantic_seg
`Collect`
- add: img_meta (the keys of img_meta is specified by `meta_keys`)
- remove: all other keys except for those specified by `keys`
### Test time augmentation
`MultiScaleFlipAug`
\ No newline at end of file
docs/GETTING_STARTED.md
View file @ 0d5233a3
......@@ -89,12 +89,10 @@ model = init_detector(config_file, checkpoint_file, device='cuda:0')
# test a single image and show the results
img = 'test.jpg' # or img = mmcv.imread(img), which will only load it once
result = inference_detector(model, img)
# visualize the results in a new window
show_result(img, result, model.CLASSES)
# test a list of images and write the results to image files
imgs = ['test1.jpg', 'test2.jpg']
for i, result in enumerate(inference_detector(model, imgs)):
show_result(imgs[i], result, model.CLASSES, out_file='result_{}.jpg'.format(i))
# or save the visualization results to image files
show_result(img, result, model.CLASSES, out_file='result.jpg')
# test a video and show the results
video = mmcv.VideoReader('video.mp4')
......
mmdet/apis/inference.py
View file @ 0d5233a3
......@@ -5,11 +5,11 @@ import mmcv
import numpy as np
import pycocotools.mask as maskUtils
import torch
from mmcv.parallel import collate, scatter
from mmcv.runner import load_checkpoint
from mmdet.core import get_classes
from mmdet.datasets import to_tensor
from mmdet.datasets.transforms import ImageTransform
from mmdet.datasets.pipelines import Compose
from mmdet.models import build_detector
......@@ -46,7 +46,16 @@ def init_detector(config, checkpoint=None, device='cuda:0'):
return model
def inference_detector(model, imgs):
class LoadImage(object):
def __call__(self, results):
img = mmcv.imread(results['img'])
results['img'] = img
results['ori_shape'] = img.shape
return results
def inference_detector(model, img):
"""Inference image(s) with the detector.
Args:
......@@ -59,45 +68,19 @@ def inference_detector(model, imgs):
detection results directly.
"""
cfg = model.cfg
img_transform = ImageTransform(
size_divisor=cfg.data.test.size_divisor, **cfg.img_norm_cfg)
device = next(model.parameters()).device # model device
if not isinstance(imgs, list):
return _inference_single(model, imgs, img_transform, device)
else:
return _inference_generator(model, imgs, img_transform, device)
def _prepare_data(img, img_transform, cfg, device):
ori_shape = img.shape
img, img_shape, pad_shape, scale_factor = img_transform(
img,
scale=cfg.data.test.img_scale,
keep_ratio=cfg.data.test.get('resize_keep_ratio', True))
img = to_tensor(img).to(device).unsqueeze(0)
img_meta = [
dict(
ori_shape=ori_shape,
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=False)
]
return dict(img=[img], img_meta=[img_meta])
def _inference_single(model, img, img_transform, device):
img = mmcv.imread(img)
data = _prepare_data(img, img_transform, model.cfg, device)
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = scatter(collate([data], samples_per_gpu=1), [device])[0]
# forward the model
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
return result
def _inference_generator(model, imgs, img_transform, device):
for img in imgs:
yield _inference_single(model, img, img_transform, device)
return result
# TODO: merge this method with the one in BaseDetector
......
mmdet/core/evaluation/eval_hooks.py
View file @ 0d5233a3
......@@ -78,12 +78,12 @@ class DistEvalmAPHook(DistEvalHook):
def evaluate(self, runner, results):
gt_bboxes = []
gt_labels = []
gt_ignore = [] if self.dataset.with_crowd else None
gt_ignore = []
for i in range(len(self.dataset)):
ann = self.dataset.get_ann_info(i)
bboxes = ann['bboxes']
labels = ann['labels']
if gt_ignore is not None:
if 'bboxes_ignore' in ann:
ignore = np.concatenate([
np.zeros(bboxes.shape[0], dtype=np.bool),
np.ones(ann['bboxes_ignore'].shape[0], dtype=np.bool)
......@@ -93,6 +93,8 @@ class DistEvalmAPHook(DistEvalHook):
labels = np.concatenate([labels, ann['labels_ignore']])
gt_bboxes.append(bboxes)
gt_labels.append(labels)
if not gt_ignore:
gt_ignore = None
# If the dataset is VOC2007, then use 11 points mAP evaluation.
if hasattr(self.dataset, 'year') and self.dataset.year == 2007:
ds_name = 'voc07'
......
mmdet/datasets/__init__.py
View file @ 0d5233a3
......@@ -6,7 +6,6 @@ from .dataset_wrappers import ConcatDataset, RepeatDataset
from .extra_aug import ExtraAugmentation
from .loader import DistributedGroupSampler, GroupSampler, build_dataloader
from .registry import DATASETS
from .utils import random_scale, show_ann, to_tensor
from .voc import VOCDataset
from .wider_face import WIDERFaceDataset
from .xml_style import XMLDataset
......@@ -14,7 +13,6 @@ from .xml_style import XMLDataset
__all__ = [
'CustomDataset', 'XMLDataset', 'CocoDataset', 'VOCDataset',
'CityscapesDataset', 'GroupSampler', 'DistributedGroupSampler',
'build_dataloader', 'to_tensor', 'random_scale', 'show_ann',
'ConcatDataset', 'RepeatDataset', 'ExtraAugmentation', 'WIDERFaceDataset',
'DATASETS', 'build_dataset'
'build_dataloader', 'ConcatDataset', 'RepeatDataset', 'ExtraAugmentation',
'WIDERFaceDataset', 'DATASETS', 'build_dataset'
]
mmdet/datasets/coco.py
View file @ 0d5233a3
......@@ -42,7 +42,7 @@ class CocoDataset(CustomDataset):
img_id = self.img_infos[idx]['id']
ann_ids = self.coco.getAnnIds(imgIds=[img_id])
ann_info = self.coco.loadAnns(ann_ids)
return self._parse_ann_info(ann_info, self.with_mask)
return self._parse_ann_info(self.img_infos[idx], ann_info)
def _filter_imgs(self, min_size=32):
"""Filter images too small or without ground truths."""
......@@ -55,7 +55,7 @@ class CocoDataset(CustomDataset):
valid_inds.append(i)
return valid_inds
def _parse_ann_info(self, ann_info, with_mask=True):
def _parse_ann_info(self, img_info, ann_info):
"""Parse bbox and mask annotation.
Args:
......@@ -64,19 +64,14 @@ class CocoDataset(CustomDataset):
Returns:
dict: A dict containing the following keys: bboxes, bboxes_ignore,
labels, masks, mask_polys, poly_lens.
labels, masks, seg_map. "masks" are raw annotations and not
decoded into binary masks.
"""
gt_bboxes = []
gt_labels = []
gt_bboxes_ignore = []
# Two formats are provided.
# 1. mask: a binary map of the same size of the image.
# 2. polys: each mask consists of one or several polys, each poly is a
# list of float.
if with_mask:
gt_masks = []
gt_mask_polys = []
gt_poly_lens = []
gt_masks_ann = []
for i, ann in enumerate(ann_info):
if ann.get('ignore', False):
continue
......@@ -84,19 +79,13 @@ class CocoDataset(CustomDataset):
if ann['area'] <= 0 or w < 1 or h < 1:
continue
bbox = [x1, y1, x1 + w - 1, y1 + h - 1]
if ann['iscrowd']:
if ann.get('iscrowd', False):
gt_bboxes_ignore.append(bbox)
else:
gt_bboxes.append(bbox)
gt_labels.append(self.cat2label[ann['category_id']])
if with_mask:
gt_masks.append(self.coco.annToMask(ann))
mask_polys = [
p for p in ann['segmentation'] if len(p) >= 6
] # valid polygons have >= 3 points (6 coordinates)
poly_lens = [len(p) for p in mask_polys]
gt_mask_polys.append(mask_polys)
gt_poly_lens.extend(poly_lens)
gt_masks_ann.append(ann['segmentation'])
if gt_bboxes:
gt_bboxes = np.array(gt_bboxes, dtype=np.float32)
gt_labels = np.array(gt_labels, dtype=np.int64)
......@@ -109,12 +98,13 @@ class CocoDataset(CustomDataset):
else:
gt_bboxes_ignore = np.zeros((0, 4), dtype=np.float32)
seg_map = img_info['filename'].replace('jpg', 'png')
ann = dict(
bboxes=gt_bboxes, labels=gt_labels, bboxes_ignore=gt_bboxes_ignore)
bboxes=gt_bboxes,
labels=gt_labels,
bboxes_ignore=gt_bboxes_ignore,
masks=gt_masks_ann,
seg_map=seg_map)
if with_mask:
ann['masks'] = gt_masks
# poly format is not used in the current implementation
ann['mask_polys'] = gt_mask_polys
ann['poly_lens'] = gt_poly_lens
return ann
mmdet/datasets/custom.py
View file @ 0d5233a3
import os.path as osp
import warnings
import mmcv
import numpy as np
from imagecorruptions import corrupt
from mmcv.parallel import DataContainer as DC
from torch.utils.data import Dataset
from .extra_aug import ExtraAugmentation
from .pipelines import Compose
from .registry import DATASETS
from .transforms import (BboxTransform, ImageTransform, MaskTransform,
Numpy2Tensor, SegMapTransform)
from .utils import random_scale, to_tensor
@DATASETS.register_module
......@@ -27,7 +21,7 @@ class CustomDataset(Dataset):
'ann': {
'bboxes': <np.ndarray> (n, 4),
'labels': <np.ndarray> (n, ),
'bboxes_ignore': <np.ndarray> (k, 4),
'bboxes_ignore': <np.ndarray> (k, 4), (optional field)
'labels_ignore': <np.ndarray> (k, 4) (optional field)
}
},
......@@ -41,33 +35,35 @@ class CustomDataset(Dataset):
def __init__(self,
ann_file,
img_prefix,
img_scale,
img_norm_cfg,
multiscale_mode='value',
size_divisor=None,
proposal_file=None,
num_max_proposals=1000,
flip_ratio=0,
with_mask=True,
with_crowd=True,
with_label=True,
with_semantic_seg=False,
pipeline,
data_root=None,
img_prefix=None,
seg_prefix=None,
seg_scale_factor=1,
extra_aug=None,
resize_keep_ratio=True,
corruption=None,
corruption_severity=1,
skip_img_without_anno=True,
proposal_file=None,
test_mode=False):
# prefix of images path
self.ann_file = ann_file
self.data_root = data_root
self.img_prefix = img_prefix
self.seg_prefix = seg_prefix
self.proposal_file = proposal_file
self.test_mode = test_mode
# join paths if data_root is specified
if self.data_root is not None:
if not osp.isabs(self.ann_file):
self.ann_file = osp.join(self.data_root, self.ann_file)
if not (self.img_prefix is None or osp.isabs(self.img_prefix)):
self.img_prefix = osp.join(self.data_root, self.img_prefix)
if not (self.seg_prefix is None or osp.isabs(self.seg_prefix)):
self.seg_prefix = osp.join(self.data_root, self.seg_prefix)
if not (self.proposal_file is None
or osp.isabs(self.proposal_file)):
self.proposal_file = osp.join(self.data_root,
self.proposal_file)
# load annotations (and proposals)
self.img_infos = self.load_annotations(ann_file)
if proposal_file is not None:
self.proposals = self.load_proposals(proposal_file)
self.img_infos = self.load_annotations(self.ann_file)
if self.proposal_file is not None:
self.proposals = self.load_proposals(self.proposal_file)
else:
self.proposals = None
# filter images with no annotation during training
......@@ -76,67 +72,11 @@ class CustomDataset(Dataset):
self.img_infos = [self.img_infos[i] for i in valid_inds]
if self.proposals is not None:
self.proposals = [self.proposals[i] for i in valid_inds]
# (long_edge, short_edge) or [(long1, short1), (long2, short2), ...]
self.img_scales = img_scale if isinstance(img_scale,
list) else [img_scale]
assert mmcv.is_list_of(self.img_scales, tuple)
# normalization configs
self.img_norm_cfg = img_norm_cfg
# multi-scale mode (only applicable for multi-scale training)
self.multiscale_mode = multiscale_mode
assert multiscale_mode in ['value', 'range']
# max proposals per image
self.num_max_proposals = num_max_proposals
# flip ratio
self.flip_ratio = flip_ratio
assert flip_ratio >= 0 and flip_ratio <= 1
# padding border to ensure the image size can be divided by
# size_divisor (used for FPN)
self.size_divisor = size_divisor
# with mask or not (reserved field, takes no effect)
self.with_mask = with_mask
# some datasets provide bbox annotations as ignore/crowd/difficult,
# if `with_crowd` is True, then these info is returned.
self.with_crowd = with_crowd
# with label is False for RPN
self.with_label = with_label
# with semantic segmentation (stuff) annotation or not
self.with_seg = with_semantic_seg
# prefix of semantic segmentation map path
self.seg_prefix = seg_prefix
# rescale factor for segmentation maps
self.seg_scale_factor = seg_scale_factor
# in test mode or not
self.test_mode = test_mode
# set group flag for the sampler
if not self.test_mode:
self._set_group_flag()
# transforms
self.img_transform = ImageTransform(
size_divisor=self.size_divisor, **self.img_norm_cfg)
self.bbox_transform = BboxTransform()
self.mask_transform = MaskTransform()
self.seg_transform = SegMapTransform(self.size_divisor)
self.numpy2tensor = Numpy2Tensor()
# if use extra augmentation
if extra_aug is not None:
self.extra_aug = ExtraAugmentation(**extra_aug)
else:
self.extra_aug = None
# image rescale if keep ratio
self.resize_keep_ratio = resize_keep_ratio
self.skip_img_without_anno = skip_img_without_anno
# corruptions
self.corruption = corruption
self.corruption_severity = corruption_severity
# processing pipeline
self.pipeline = Compose(pipeline)
def __len__(self):
return len(self.img_infos)
......@@ -150,6 +90,13 @@ class CustomDataset(Dataset):
def get_ann_info(self, idx):
return self.img_infos[idx]['ann']
def pre_pipeline(self, results):
results['img_prefix'] = self.img_prefix
results['seg_prefix'] = self.seg_prefix
results['proposal_file'] = self.proposal_file
results['bbox_fields'] = []
results['mask_fields'] = []
def _filter_imgs(self, min_size=32):
"""Filter images too small."""
valid_inds = []
......@@ -186,164 +133,17 @@ class CustomDataset(Dataset):
def prepare_train_img(self, idx):
img_info = self.img_infos[idx]
# load image
img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
# corruption
if self.corruption is not None:
img = corrupt(
img,
severity=self.corruption_severity,
corruption_name=self.corruption)
# load proposals if necessary
if self.proposals is not None:
proposals = self.proposals[idx][:self.num_max_proposals]
# TODO: Handle empty proposals properly. Currently images with
# no proposals are just ignored, but they can be used for
# training in concept.
if len(proposals) == 0:
return None
if not (proposals.shape[1] == 4 or proposals.shape[1] == 5):
raise AssertionError(
'proposals should have shapes (n, 4) or (n, 5), '
'but found {}'.format(proposals.shape))
if proposals.shape[1] == 5:
scores = proposals[:, 4, None]
proposals = proposals[:, :4]
else:
scores = None
ann = self.get_ann_info(idx)
gt_bboxes = ann['bboxes']
gt_labels = ann['labels']
if self.with_crowd:
gt_bboxes_ignore = ann['bboxes_ignore']
# skip the image if there is no valid gt bbox
if len(gt_bboxes) == 0 and self.skip_img_without_anno:
warnings.warn('Skip the image "%s" that has no valid gt bbox' %
osp.join(self.img_prefix, img_info['filename']))
return None
# extra augmentation
if self.extra_aug is not None:
img, gt_bboxes, gt_labels = self.extra_aug(img, gt_bboxes,
gt_labels)
# apply transforms
flip = True if np.random.rand() < self.flip_ratio else False
# randomly sample a scale
img_scale = random_scale(self.img_scales, self.multiscale_mode)
img, img_shape, pad_shape, scale_factor = self.img_transform(
img, img_scale, flip, keep_ratio=self.resize_keep_ratio)
img = img.copy()
if self.with_seg:
gt_seg = mmcv.imread(
osp.join(self.seg_prefix,
img_info['filename'].replace('jpg', 'png')),
flag='unchanged')
gt_seg = self.seg_transform(gt_seg.squeeze(), img_scale, flip)
gt_seg = mmcv.imrescale(
gt_seg, self.seg_scale_factor, interpolation='nearest')
gt_seg = gt_seg[None, ...]
ann_info = self.get_ann_info(idx)
results = dict(img_info=img_info, ann_info=ann_info)
if self.proposals is not None:
proposals = self.bbox_transform(proposals, img_shape, scale_factor,
flip)
proposals = np.hstack([proposals, scores
]) if scores is not None else proposals
gt_bboxes = self.bbox_transform(gt_bboxes, img_shape, scale_factor,
flip)
if self.with_crowd:
gt_bboxes_ignore = self.bbox_transform(gt_bboxes_ignore, img_shape,
scale_factor, flip)
if self.with_mask:
gt_masks = self.mask_transform(ann['masks'], pad_shape,
scale_factor, flip)
ori_shape = (img_info['height'], img_info['width'], 3)
img_meta = dict(
ori_shape=ori_shape,
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
data = dict(
img=DC(to_tensor(img), stack=True),
img_meta=DC(img_meta, cpu_only=True),
gt_bboxes=DC(to_tensor(gt_bboxes)))
if self.proposals is not None:
data['proposals'] = DC(to_tensor(proposals))
if self.with_label:
data['gt_labels'] = DC(to_tensor(gt_labels))
if self.with_crowd:
data['gt_bboxes_ignore'] = DC(to_tensor(gt_bboxes_ignore))
if self.with_mask:
data['gt_masks'] = DC(gt_masks, cpu_only=True)
if self.with_seg:
data['gt_semantic_seg'] = DC(to_tensor(gt_seg), stack=True)
return data
results['proposals'] = self.proposals[idx]
self.pre_pipeline(results)
return self.pipeline(results)
def prepare_test_img(self, idx):
"""Prepare an image for testing (multi-scale and flipping)"""
img_info = self.img_infos[idx]
img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
# corruption
if self.corruption is not None:
img = corrupt(
img,
severity=self.corruption_severity,
corruption_name=self.corruption)
# load proposals if necessary
if self.proposals is not None:
proposal = self.proposals[idx][:self.num_max_proposals]
if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
raise AssertionError(
'proposals should have shapes (n, 4) or (n, 5), '
'but found {}'.format(proposal.shape))
else:
proposal = None
def prepare_single(img, scale, flip, proposal=None):
_img, img_shape, pad_shape, scale_factor = self.img_transform(
img, scale, flip, keep_ratio=self.resize_keep_ratio)
_img = to_tensor(_img)
_img_meta = dict(
ori_shape=(img_info['height'], img_info['width'], 3),
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
if proposal is not None:
if proposal.shape[1] == 5:
score = proposal[:, 4, None]
proposal = proposal[:, :4]
else:
score = None
_proposal = self.bbox_transform(proposal, img_shape,
scale_factor, flip)
_proposal = np.hstack([_proposal, score
]) if score is not None else _proposal
_proposal = to_tensor(_proposal)
else:
_proposal = None
return _img, _img_meta, _proposal
imgs = []
img_metas = []
proposals = []
for scale in self.img_scales:
_img, _img_meta, _proposal = prepare_single(
img, scale, False, proposal)
imgs.append(_img)
img_metas.append(DC(_img_meta, cpu_only=True))
proposals.append(_proposal)
if self.flip_ratio > 0:
_img, _img_meta, _proposal = prepare_single(
img, scale, True, proposal)
imgs.append(_img)
img_metas.append(DC(_img_meta, cpu_only=True))
proposals.append(_proposal)
data = dict(img=imgs, img_meta=img_metas)
results = dict(img_info=img_info)
if self.proposals is not None:
data['proposals'] = proposals
return data
results['proposals'] = self.proposals[idx]
self.pre_pipeline(results)
return self.pipeline(results)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment