Skip to content

GitLab

Commit 450cfb73 authored by yhcao6's avatar yhcao6
Browse files

support VOC dataset

parent 40325555
Hide whitespace changes
Inline Side-by-side
Showing with 273 additions and 8 deletions
configs/ssd300_coco.py
View file @ 450cfb73
......@@ -46,8 +46,8 @@ 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)
data = dict(
imgs_per_gpu=4,
workers_per_gpu=2,
imgs_per_gpu=8,
workers_per_gpu=3,
train=dict(
type='RepeatDataset',
dataset=dict(
......@@ -101,7 +101,7 @@ data = dict(
test_mode=True,
resize_keep_ratio=False))
# optimizer
optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# learning policy
lr_config = dict(
......
configs/ssd300_voc.py 0 → 100644
View file @ 450cfb73
# model settings
model = dict(
type='SingleStageDetector',
pretrained='data/vgg_backbone.pth',
backbone=dict(
type='SSDVGG',
input_size=300,
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
l2_norm_scale=20),
neck=None,
bbox_head=dict(
type='SSDHead',
input_size=300,
in_channels=(512, 1024, 512, 256, 256, 256),
num_classes=21,
anchor_strides=(8, 16, 32, 64, 100, 300),
basesize_ratio_range=(0.2, 0.9),
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)))
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False)
test_cfg = dict(
nms=dict(type='nms', iou_thr=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
# model training and testing settings
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
data = dict(
imgs_per_gpu=8,
workers_per_gpu=3,
train=dict(
type='RepeatDataset',
dataset=dict(
type=dataset_type,
ann_file=[
data_root + 'VOC2007/ImageSets/Main/trainval.txt',
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=True,
test_mode=False,
extra_aug=dict(
photo_metric_distortion=dict(
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
expand=dict(
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 4)),
random_crop=dict(
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
resize_keep_ratio=False),
times=20),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False))
# optimizer
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ssd300_voc'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/ssd512_coco.py
View file @ 450cfb73
......@@ -46,8 +46,8 @@ 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)
data = dict(
imgs_per_gpu=4,
workers_per_gpu=2,
imgs_per_gpu=8,
workers_per_gpu=3,
train=dict(
type='RepeatDataset',
dataset=dict(
......@@ -101,7 +101,7 @@ data = dict(
test_mode=True,
resize_keep_ratio=False))
# optimizer
optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# learning policy
lr_config = dict(
......
configs/ssd512_voc.py 0 → 100644
View file @ 450cfb73
# model settings
model = dict(
type='SingleStageDetector',
pretrained='data/vgg_backbone.pth',
backbone=dict(
type='SSDVGG',
input_size=512,
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
l2_norm_scale=20),
neck=None,
bbox_head=dict(
type='SSDHead',
input_size=512,
in_channels=(512, 1024, 512, 256, 256, 256, 256),
num_classes=81,
anchor_strides=(8, 16, 32, 64, 128, 256, 512),
basesize_ratio_range=(0.1, 0.9),
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False)
test_cfg = dict(
nms=dict(type='nms', iou_thr=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
# model training and testing settings
# dataset settings
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)
data = dict(
imgs_per_gpu=8,
workers_per_gpu=3,
train=dict(
type='RepeatDataset',
dataset=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),
times=10),
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),
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))
# optimizer
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ssd512_voc'
load_from = None
resume_from = None
workflow = [('train', 1)]
mmdet/models/single_stage_heads/ssd_head.py
View file @ 450cfb73
......@@ -55,8 +55,12 @@ class SSDHead(nn.Module):
min_sizes.append(int(input_size * r / 100))
max_sizes.append(int(input_size * (r + step) / 100))
if input_size == 300:
min_sizes.insert(0, int(input_size * 7 / 100))
max_sizes.insert(0, int(input_size * 15 / 100))
if basesize_ratio_range[0] == 0.15:
min_sizes.insert(0, int(input_size * 7 / 100))
max_sizes.insert(0, int(input_size * 15 / 100))
elif basesize_ratio_range[0] == 0.2:
min_sizes.insert(0, int(input_size * 10 / 100))
max_sizes.insert(0, int(input_size * 20 / 100))
elif input_size == 512:
min_sizes.insert(0, int(input_size * 4 / 100))
max_sizes.insert(0, int(input_size * 10 / 100))
......
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