Skip to content
项目
群组
代码片段
帮助
当前项目
正在载入...
登录 / 注册
切换导航面板
Y
yolov5
项目
项目
详情
活动
周期分析
仓库
仓库
文件
提交
分支
标签
贡献者
图表
比较
统计图
议题
0
议题
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
CI / CD
CI / CD
流水线
作业
日程
统计图
Wiki
Wiki
代码片段
代码片段
成员
成员
折叠边栏
关闭边栏
活动
图像
聊天
创建新问题
作业
提交
问题看板
Open sidebar
Administrator
yolov5
Commits
4447f4b9
Unverified
提交
4447f4b9
authored
8月 21, 2020
作者:
Glenn Jocher
提交者:
GitHub
8月 21, 2020
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
--resume to same runs/exp directory (#765)
* initial commit * add weight backup dir on resume
上级
5e0b90de
隐藏空白字符变更
内嵌
并排
正在显示
1 个修改的文件
包含
15 行增加
和
11 行删除
+15
-11
train.py
train.py
+15
-11
没有找到文件。
train.py
浏览文件 @
4447f4b9
import
argparse
import
logging
import
math
import
os
import
random
import
shutil
import
time
import
logging
from
pathlib
import
Path
import
numpy
as
np
...
...
@@ -34,10 +35,10 @@ logger = logging.getLogger(__name__)
def
train
(
hyp
,
opt
,
device
,
tb_writer
=
None
):
logger
.
info
(
f
'Hyperparameters {hyp}'
)
log_dir
=
Path
(
tb_writer
.
log_dir
)
if
tb_writer
else
Path
(
opt
.
logdir
)
/
'evolve'
# logging directory
wdir
=
str
(
log_dir
/
'weights'
)
+
os
.
sep
# weights directory
wdir
=
log_dir
/
'weights'
# weights directory
os
.
makedirs
(
wdir
,
exist_ok
=
True
)
last
=
wdir
+
'last.pt'
best
=
wdir
+
'best.pt'
last
=
wdir
/
'last.pt'
best
=
wdir
/
'best.pt'
results_file
=
str
(
log_dir
/
'results.txt'
)
epochs
,
batch_size
,
total_batch_size
,
weights
,
rank
=
\
opt
.
epochs
,
opt
.
batch_size
,
opt
.
total_batch_size
,
opt
.
weights
,
opt
.
global_rank
...
...
@@ -131,6 +132,7 @@ def train(hyp, opt, device, tb_writer=None):
start_epoch
=
ckpt
[
'epoch'
]
+
1
if
opt
.
resume
:
assert
start_epoch
>
0
,
'
%
s training to
%
g epochs is finished, nothing to resume.'
%
(
weights
,
epochs
)
shutil
.
copytree
(
wdir
,
wdir
.
parent
/
f
'weights_backup_epoch{start_epoch - 1}'
)
# save previous weights
if
epochs
<
start_epoch
:
logger
.
info
(
'
%
s has been trained for
%
g epochs. Fine-tuning for
%
g additional epochs.'
%
(
weights
,
ckpt
[
'epoch'
],
epochs
))
...
...
@@ -365,13 +367,13 @@ def train(hyp, opt, device, tb_writer=None):
if
rank
in
[
-
1
,
0
]:
# Strip optimizers
n
=
(
'_'
if
len
(
opt
.
name
)
and
not
opt
.
name
.
isnumeric
()
else
''
)
+
opt
.
name
fresults
,
flast
,
fbest
=
'results
%
s.txt'
%
n
,
wdir
+
'last
%
s.pt'
%
n
,
wdir
+
'best
%
s.pt'
%
n
for
f1
,
f2
in
zip
([
wdir
+
'last.pt'
,
wdir
+
'best.pt'
,
'results.txt'
],
[
flast
,
fbest
,
fresults
]):
fresults
,
flast
,
fbest
=
'results
%
s.txt'
%
n
,
wdir
/
f
'last{n}.pt'
,
wdir
/
f
'best{n}.pt'
for
f1
,
f2
in
zip
([
wdir
/
'last.pt'
,
wdir
/
'best.pt'
,
'results.txt'
],
[
flast
,
fbest
,
fresults
]):
if
os
.
path
.
exists
(
f1
):
os
.
rename
(
f1
,
f2
)
# rename
i
spt
=
f2
.
endswith
(
'.pt'
)
# is *.pt
strip_optimizer
(
f2
)
if
ispt
else
None
# strip optimizer
os
.
system
(
'gsutil cp
%
s gs://
%
s/weights'
%
(
f2
,
opt
.
bucket
))
if
opt
.
bucket
and
isp
t
else
None
# upload
i
f
str
(
f2
)
.
endswith
(
'.pt'
):
# is *.pt
strip_optimizer
(
f2
)
# strip optimizer
os
.
system
(
'gsutil cp
%
s gs://
%
s/weights'
%
(
f2
,
opt
.
bucket
))
if
opt
.
bucke
t
else
None
# upload
# Finish
if
not
opt
.
evolve
:
plot_results
(
save_dir
=
log_dir
)
# save as results.png
...
...
@@ -421,8 +423,9 @@ if __name__ == '__main__':
# Resume
if
opt
.
resume
:
# resume an interrupted run
ckpt
=
opt
.
resume
if
isinstance
(
opt
.
resume
,
str
)
else
get_latest_run
()
# specified or most recent path
log_dir
=
Path
(
ckpt
)
.
parent
.
parent
# runs/exp0
assert
os
.
path
.
isfile
(
ckpt
),
'ERROR: --resume checkpoint does not exist'
with
open
(
Path
(
ckpt
)
.
parent
.
parent
/
'opt.yaml'
)
as
f
:
with
open
(
log_dir
/
'opt.yaml'
)
as
f
:
opt
=
argparse
.
Namespace
(
**
yaml
.
load
(
f
,
Loader
=
yaml
.
FullLoader
))
# replace
opt
.
cfg
,
opt
.
weights
,
opt
.
resume
=
''
,
ckpt
,
True
logger
.
info
(
'Resuming training from
%
s'
%
ckpt
)
...
...
@@ -432,6 +435,7 @@ if __name__ == '__main__':
opt
.
data
,
opt
.
cfg
,
opt
.
hyp
=
check_file
(
opt
.
data
),
check_file
(
opt
.
cfg
),
check_file
(
opt
.
hyp
)
# check files
assert
len
(
opt
.
cfg
)
or
len
(
opt
.
weights
),
'either --cfg or --weights must be specified'
opt
.
img_size
.
extend
([
opt
.
img_size
[
-
1
]]
*
(
2
-
len
(
opt
.
img_size
)))
# extend to 2 sizes (train, test)
log_dir
=
increment_dir
(
Path
(
opt
.
logdir
)
/
'exp'
,
opt
.
name
)
# runs/exp1
device
=
select_device
(
opt
.
device
,
batch_size
=
opt
.
batch_size
)
...
...
@@ -453,7 +457,7 @@ if __name__ == '__main__':
tb_writer
=
None
if
opt
.
global_rank
in
[
-
1
,
0
]:
logger
.
info
(
'Start Tensorboard with "tensorboard --logdir
%
s", view at http://localhost:6006/'
%
opt
.
logdir
)
tb_writer
=
SummaryWriter
(
log_dir
=
increment_dir
(
Path
(
opt
.
logdir
)
/
'exp'
,
opt
.
name
))
# runs/exp
tb_writer
=
SummaryWriter
(
log_dir
=
log_dir
)
# runs/exp0
train
(
hyp
,
opt
,
device
,
tb_writer
)
...
...
编写
预览
Markdown
格式
0%
重试
或
添加新文件
添加附件
取消
您添加了
0
人
到此讨论。请谨慎行事。
请先完成此评论的编辑!
取消
请
注册
或者
登录
后发表评论