Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
PaddleDetection
提交
beaa62a7
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 2 年 前同步成功
通知
708
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleDetection
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
提交
beaa62a7
编写于
7月 07, 2020
作者:
L
longxiang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update yolov3
上级
a66dfe9c
变更
5
展开全部
隐藏空白更改
内联
并排
Showing
5 changed file
with
908 addition
and
527 deletion
+908
-527
configs/ppyolo/ppyolo.yml
configs/ppyolo/ppyolo.yml
+91
-0
configs/ppyolo/ppyolo_lb.yml
configs/ppyolo/ppyolo_lb.yml
+91
-0
configs/ppyolo/ppyolo_reader.yml
configs/ppyolo/ppyolo_reader.yml
+111
-0
ppdet/modeling/anchor_heads/yolo_head.py
ppdet/modeling/anchor_heads/yolo_head.py
+590
-526
ppdet/modeling/ops.py
ppdet/modeling/ops.py
+25
-1
未找到文件。
configs/ppyolo/ppyolo.yml
0 → 100644
浏览文件 @
beaa62a7
architecture
:
YOLOv3
use_gpu
:
true
max_iters
:
500000
log_smooth_window
:
100
log_iter
:
100
save_dir
:
output
snapshot_iter
:
10000
metric
:
COCO
pretrain_weights
:
https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
weights
:
output/ppyolo/model_final
num_classes
:
80
use_fine_grained_loss
:
true
use_ema
:
true
ema_decay
:
0.9998
YOLOv3
:
backbone
:
ResNet
yolo_head
:
YOLOv3Head
use_fine_grained_loss
:
true
ResNet
:
norm_type
:
sync_bn
freeze_at
:
0
freeze_norm
:
false
norm_decay
:
0.
depth
:
50
feature_maps
:
[
3
,
4
,
5
]
variant
:
d
dcn_v2_stages
:
[
5
]
YOLOv3Head
:
anchor_masks
:
[[
6
,
7
,
8
],
[
3
,
4
,
5
],
[
0
,
1
,
2
]]
anchors
:
[[
10
,
13
],
[
16
,
30
],
[
33
,
23
],
[
30
,
61
],
[
62
,
45
],
[
59
,
119
],
[
116
,
90
],
[
156
,
198
],
[
373
,
326
]]
norm_decay
:
0.
coord_conv
:
true
iou_aware
:
true
iou_aware_factor
:
0.4
scale_x_y
:
1.05
spp
:
true
yolo_loss
:
YOLOv3Loss
nms
:
background_label
:
-1
keep_top_k
:
100
# nms_threshold: 0.45
# nms_top_k: 1000
normalized
:
false
score_threshold
:
0.01
drop_block
:
true
YOLOv3Loss
:
batch_size
:
24
ignore_thresh
:
0.7
scale_x_y
:
1.05
label_smooth
:
false
use_fine_grained_loss
:
true
iou_loss
:
IouLoss
iou_aware_loss
:
IouAwareLoss
IouLoss
:
loss_weight
:
2.5
max_height
:
608
max_width
:
608
IouAwareLoss
:
loss_weight
:
1.0
max_height
:
608
max_width
:
608
LearningRate
:
base_lr
:
0.00333
schedulers
:
-
!PiecewiseDecay
gamma
:
0.1
milestones
:
-
400000
-
450000
-
!LinearWarmup
start_factor
:
0.
steps
:
4000
OptimizerBuilder
:
optimizer
:
momentum
:
0.9
type
:
Momentum
regularizer
:
factor
:
0.0005
type
:
L2
_READER_
:
'
ppyolo_reader.yml'
configs/ppyolo/ppyolo_lb.yml
0 → 100644
浏览文件 @
beaa62a7
architecture
:
YOLOv3
use_gpu
:
true
max_iters
:
250000
log_smooth_window
:
100
log_iter
:
100
save_dir
:
output
snapshot_iter
:
10000
metric
:
COCO
pretrain_weights
:
https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
weights
:
output/ppyolo_lb/model_final
num_classes
:
80
use_fine_grained_loss
:
true
use_ema
:
true
ema_decay
:
0.9998
YOLOv3
:
backbone
:
ResNet
yolo_head
:
YOLOv3Head
use_fine_grained_loss
:
true
ResNet
:
norm_type
:
sync_bn
freeze_at
:
0
freeze_norm
:
false
norm_decay
:
0.
depth
:
50
feature_maps
:
[
3
,
4
,
5
]
variant
:
d
dcn_v2_stages
:
[
5
]
YOLOv3Head
:
anchor_masks
:
[[
6
,
7
,
8
],
[
3
,
4
,
5
],
[
0
,
1
,
2
]]
anchors
:
[[
10
,
13
],
[
16
,
30
],
[
33
,
23
],
[
30
,
61
],
[
62
,
45
],
[
59
,
119
],
[
116
,
90
],
[
156
,
198
],
[
373
,
326
]]
norm_decay
:
0.
coord_conv
:
true
iou_aware
:
true
iou_aware_factor
:
0.4
scale_x_y
:
1.05
spp
:
true
yolo_loss
:
YOLOv3Loss
nms
:
background_label
:
-1
keep_top_k
:
100
# nms_threshold: 0.45
# nms_top_k: 1000
normalized
:
false
score_threshold
:
0.01
drop_block
:
true
YOLOv3Loss
:
batch_size
:
24
ignore_thresh
:
0.7
scale_x_y
:
1.05
label_smooth
:
false
use_fine_grained_loss
:
true
iou_loss
:
IouLoss
iou_aware_loss
:
IouAwareLoss
IouLoss
:
loss_weight
:
2.5
max_height
:
608
max_width
:
608
IouAwareLoss
:
loss_weight
:
1.0
max_height
:
608
max_width
:
608
LearningRate
:
base_lr
:
0.01
schedulers
:
-
!PiecewiseDecay
gamma
:
0.1
milestones
:
-
150000
-
200000
-
!LinearWarmup
start_factor
:
0.
steps
:
4000
OptimizerBuilder
:
optimizer
:
momentum
:
0.9
type
:
Momentum
regularizer
:
factor
:
0.0005
type
:
L2
_READER_
:
'
ppyolo_reader.yml'
configs/ppyolo/ppyolo_reader.yml
0 → 100644
浏览文件 @
beaa62a7
TrainReader
:
inputs_def
:
fields
:
[
'
image'
,
'
gt_bbox'
,
'
gt_class'
,
'
gt_score'
]
num_max_boxes
:
50
dataset
:
!COCODataSet
image_dir
:
train2017
anno_path
:
annotations/instances_train2017.json
dataset_dir
:
dataset/coco
with_background
:
false
sample_transforms
:
-
!DecodeImage
to_rgb
:
True
with_mixup
:
True
-
!MixupImage
alpha
:
1.5
beta
:
1.5
-
!ColorDistort
{}
-
!RandomExpand
fill_value
:
[
123.675
,
116.28
,
103.53
]
-
!RandomCrop
{}
-
!RandomFlipImage
is_normalized
:
false
-
!NormalizeBox
{}
-
!PadBox
num_max_boxes
:
50
-
!BboxXYXY2XYWH
{}
batch_transforms
:
-
!RandomShape
sizes
:
[
320
,
352
,
384
,
416
,
448
,
480
,
512
,
544
,
576
,
608
]
random_inter
:
True
-
!NormalizeImage
mean
:
[
0.485
,
0.456
,
0.406
]
std
:
[
0.229
,
0.224
,
0.225
]
is_scale
:
True
is_channel_first
:
false
-
!Permute
to_bgr
:
false
channel_first
:
True
# Gt2YoloTarget is only used when use_fine_grained_loss set as true,
# this operator will be deleted automatically if use_fine_grained_loss
# is set as false
-
!Gt2YoloTarget
anchor_masks
:
[[
6
,
7
,
8
],
[
3
,
4
,
5
],
[
0
,
1
,
2
]]
anchors
:
[[
10
,
13
],
[
16
,
30
],
[
33
,
23
],
[
30
,
61
],
[
62
,
45
],
[
59
,
119
],
[
116
,
90
],
[
156
,
198
],
[
373
,
326
]]
downsample_ratios
:
[
32
,
16
,
8
]
batch_size
:
24
shuffle
:
true
# mixup_epoch: 250
mixup_epoch
:
25000
drop_last
:
true
worker_num
:
8
bufsize
:
4
use_process
:
true
EvalReader
:
inputs_def
:
fields
:
[
'
image'
,
'
im_size'
,
'
im_id'
]
num_max_boxes
:
50
dataset
:
!COCODataSet
image_dir
:
val2017
anno_path
:
annotations/instances_val2017.json
dataset_dir
:
dataset/coco
with_background
:
false
sample_transforms
:
-
!DecodeImage
to_rgb
:
True
-
!ResizeImage
target_size
:
608
interp
:
2
-
!NormalizeImage
mean
:
[
0.485
,
0.456
,
0.406
]
std
:
[
0.229
,
0.224
,
0.225
]
is_scale
:
True
is_channel_first
:
false
-
!PadBox
num_max_boxes
:
50
-
!Permute
to_bgr
:
false
channel_first
:
True
batch_size
:
8
drop_empty
:
false
worker_num
:
8
bufsize
:
4
TestReader
:
inputs_def
:
image_shape
:
[
3
,
608
,
608
]
fields
:
[
'
image'
,
'
im_size'
,
'
im_id'
]
dataset
:
!ImageFolder
anno_path
:
annotations/instances_val2017.json
with_background
:
false
sample_transforms
:
-
!DecodeImage
to_rgb
:
True
-
!ResizeImage
target_size
:
608
interp
:
2
-
!NormalizeImage
mean
:
[
0.485
,
0.456
,
0.406
]
std
:
[
0.229
,
0.224
,
0.225
]
is_scale
:
True
is_channel_first
:
false
-
!Permute
to_bgr
:
false
channel_first
:
True
batch_size
:
1
ppdet/modeling/anchor_heads/yolo_head.py
浏览文件 @
beaa62a7
此差异已折叠。
点击以展开。
ppdet/modeling/ops.py
浏览文件 @
beaa62a7
...
@@ -30,9 +30,33 @@ __all__ = [
...
@@ -30,9 +30,33 @@ __all__ = [
'GenerateProposals'
,
'MultiClassNMS'
,
'BBoxAssigner'
,
'MaskAssigner'
,
'GenerateProposals'
,
'MultiClassNMS'
,
'BBoxAssigner'
,
'MaskAssigner'
,
'RoIAlign'
,
'RoIPool'
,
'MultiBoxHead'
,
'SSDLiteMultiBoxHead'
,
'RoIAlign'
,
'RoIPool'
,
'MultiBoxHead'
,
'SSDLiteMultiBoxHead'
,
'SSDOutputDecoder'
,
'RetinaTargetAssign'
,
'RetinaOutputDecoder'
,
'ConvNorm'
,
'SSDOutputDecoder'
,
'RetinaTargetAssign'
,
'RetinaOutputDecoder'
,
'ConvNorm'
,
'DeformConvNorm'
,
'MultiClassSoftNMS'
,
'LibraBBoxAssigner'
'DeformConvNorm'
,
'MultiClassSoftNMS'
,
'LibraBBoxAssigner'
,
'MultiClassMatrixNMS'
]
]
@
register
@
serializable
class
MultiClassMatrixNMS
(
object
):
__op__
=
fluid
.
layers
.
matrix_nms
__append_doc__
=
True
def
__init__
(
self
,
score_threshold
=
.
05
,
post_threshold
=
.
01
,
nms_top_k
=-
1
,
keep_top_k
=
100
,
use_gaussian
=
False
,
gaussian_sigma
=
2.0
,
normalized
=
False
,
background_label
=
0
):
super
(
MultiClassMatrixNMS
,
self
).
__init__
()
self
.
score_threshold
=
score_threshold
self
.
nms_top_k
=
nms_top_k
self
.
keep_top_k
=
keep_top_k
self
.
score_threshold
=
score_threshold
self
.
post_threshold
=
post_threshold
self
.
use_gaussian
=
use_gaussian
self
.
normalized
=
normalized
self
.
background_label
=
background_label
def
_conv_offset
(
input
,
filter_size
,
stride
,
padding
,
act
=
None
,
name
=
None
):
def
_conv_offset
(
input
,
filter_size
,
stride
,
padding
,
act
=
None
,
name
=
None
):
out_channel
=
filter_size
*
filter_size
*
3
out_channel
=
filter_size
*
filter_size
*
3
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录