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
98a6b191
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
695
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
98a6b191
编写于
9月 21, 2020
作者:
S
still-wait
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix train batch size
上级
1394ab33
变更
2
显示空白变更内容
内联
并排
Showing
2 changed file
with
100 addition
and
6 deletion
+100
-6
configs/solov2/solov2_r50_fpn_3x.yml
configs/solov2/solov2_r50_fpn_3x.yml
+90
-0
ppdet/modeling/architectures/solov2.py
ppdet/modeling/architectures/solov2.py
+10
-6
未找到文件。
configs/solov2/solov2_r50_fpn_3x.yml
0 → 100644
浏览文件 @
98a6b191
architecture
:
SOLOv2
use_gpu
:
true
max_iters
:
270000
snapshot_iter
:
30000
log_smooth_window
:
20
save_dir
:
output
pretrain_weights
:
https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
metric
:
COCO
weights
:
output/solov2/solov2_r50_fpn_3x/model_final
num_classes
:
81
SOLOv2
:
backbone
:
ResNet
fpn
:
FPN
bbox_head
:
SOLOv2Head
mask_head
:
SOLOv2MaskHead
batch_size
:
2
ResNet
:
depth
:
50
feature_maps
:
[
2
,
3
,
4
,
5
]
freeze_at
:
2
norm_type
:
bn
FPN
:
max_level
:
6
min_level
:
2
num_chan
:
256
spatial_scale
:
[
0.03125
,
0.0625
,
0.125
,
0.25
]
reverse_out
:
True
SOLOv2Head
:
seg_feat_channels
:
512
stacked_convs
:
4
num_grids
:
[
40
,
36
,
24
,
16
,
12
]
kernel_out_channels
:
256
SOLOv2MaskHead
:
out_channels
:
128
start_level
:
0
end_level
:
3
num_classes
:
256
LearningRate
:
base_lr
:
0.01
schedulers
:
-
!PiecewiseDecay
gamma
:
0.1
milestones
:
[
180000
,
240000
]
-
!LinearWarmup
start_factor
:
0.
steps
:
1000
OptimizerBuilder
:
optimizer
:
momentum
:
0.9
type
:
Momentum
regularizer
:
factor
:
0.0001
type
:
L2
_READER_
:
'
solov2_reader.yml'
TrainReader
:
sample_transforms
:
-
!DecodeImage
to_rgb
:
true
-
!Poly2Mask
{}
-
!ResizeImage
target_size
:
[
640
,
672
,
704
,
736
,
768
,
800
]
max_size
:
1333
interp
:
1
use_cv2
:
true
resize_box
:
true
-
!RandomFlipImage
prob
:
0.5
-
!NormalizeImage
is_channel_first
:
false
is_scale
:
true
mean
:
[
0.485
,
0.456
,
0.406
]
std
:
[
0.229
,
0.224
,
0.225
]
-
!Permute
to_bgr
:
false
channel_first
:
true
batch_transforms
:
-
!PadBatch
pad_to_stride
:
32
-
!Gt2Solov2Target
num_grids
:
[
40
,
36
,
24
,
16
,
12
]
scale_ranges
:
[[
1
,
96
],
[
48
,
192
],
[
96
,
384
],
[
192
,
768
],
[
384
,
2048
]]
coord_sigma
:
0.2
ppdet/modeling/architectures/solov2.py
浏览文件 @
98a6b191
...
@@ -36,24 +36,25 @@ class SOLOv2(object):
...
@@ -36,24 +36,25 @@ class SOLOv2(object):
fpn (object): feature pyramid network instance
fpn (object): feature pyramid network instance
bbox_head (object): an `SOLOv2Head` instance
bbox_head (object): an `SOLOv2Head` instance
mask_head (object): an `SOLOv2MaskHead` instance
mask_head (object): an `SOLOv2MaskHead` instance
batch_size (int):
batch size.
train_batch_size (int): training
batch size.
"""
"""
__category__
=
'architecture'
__category__
=
'architecture'
__inject__
=
[
'backbone'
,
'fpn'
,
'bbox_head'
,
'mask_head'
]
__inject__
=
[
'backbone'
,
'fpn'
,
'bbox_head'
,
'mask_head'
]
__shared__
=
[
'train_batch_size'
]
def
__init__
(
self
,
def
__init__
(
self
,
backbone
,
backbone
,
fpn
=
None
,
fpn
=
None
,
bbox_head
=
'SOLOv2Head'
,
bbox_head
=
'SOLOv2Head'
,
mask_head
=
'SOLOv2MaskHead'
,
mask_head
=
'SOLOv2MaskHead'
,
batch_size
=
1
):
train_
batch_size
=
1
):
super
(
SOLOv2
,
self
).
__init__
()
super
(
SOLOv2
,
self
).
__init__
()
self
.
backbone
=
backbone
self
.
backbone
=
backbone
self
.
fpn
=
fpn
self
.
fpn
=
fpn
self
.
bbox_head
=
bbox_head
self
.
bbox_head
=
bbox_head
self
.
mask_head
=
mask_head
self
.
mask_head
=
mask_head
self
.
batch_size
=
batch_size
self
.
train_batch_size
=
train_
batch_size
def
build
(
self
,
feed_vars
,
mode
=
'train'
):
def
build
(
self
,
feed_vars
,
mode
=
'train'
):
im
=
feed_vars
[
'image'
]
im
=
feed_vars
[
'image'
]
...
@@ -79,6 +80,8 @@ class SOLOv2(object):
...
@@ -79,6 +80,8 @@ class SOLOv2(object):
if
not
mode
==
'train'
:
if
not
mode
==
'train'
:
self
.
batch_size
=
1
self
.
batch_size
=
1
else
:
self
.
batch_size
=
self
.
train_batch_size
mask_feat_pred
=
self
.
mask_head
.
get_output
(
body_feats
,
self
.
batch_size
)
mask_feat_pred
=
self
.
mask_head
.
get_output
(
body_feats
,
self
.
batch_size
)
...
@@ -103,9 +106,10 @@ class SOLOv2(object):
...
@@ -103,9 +106,10 @@ class SOLOv2(object):
cate_preds
,
kernel_preds
=
self
.
bbox_head
.
get_outputs
(
cate_preds
,
kernel_preds
=
self
.
bbox_head
.
get_outputs
(
body_feats
,
batch_size
=
self
.
batch_size
)
body_feats
,
batch_size
=
self
.
batch_size
)
losses
=
self
.
bbox_head
.
get_loss
(
losses
=
self
.
bbox_head
.
get_loss
(
cate_preds
,
kernel_preds
,
cate_preds
,
kernel_preds
,
mask_feat_pred
,
ins_labels
,
mask_feat_pred
,
ins_labels
,
cate_labels
,
grid_orders
,
fg_num
,
grid_offset
,
self
.
batch_size
)
cate_labels
,
grid_orders
,
fg_num
,
grid_offset
,
self
.
train_batch_size
)
total_loss
=
fluid
.
layers
.
sum
(
list
(
losses
.
values
()))
total_loss
=
fluid
.
layers
.
sum
(
list
(
losses
.
values
()))
losses
.
update
({
'loss'
:
total_loss
})
losses
.
update
({
'loss'
:
total_loss
})
return
losses
return
losses
...
...
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