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
f0007141
Unverified
提交
f0007141
authored
5月 15, 2022
作者:
Glenn Jocher
提交者:
GitHub
5月 15, 2022
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Refactor collections and fstrings (#7821)
* Update torch_utils.py * Additional code refactoring * tuples to sets * Cleanup
上级
3356f260
隐藏空白字符变更
内嵌
并排
正在显示
9 个修改的文件
包含
58 行增加
和
63 行删除
+58
-63
detect.py
detect.py
+3
-3
export.py
export.py
+3
-3
train.py
train.py
+8
-8
autoanchor.py
utils/autoanchor.py
+1
-1
dataloaders.py
utils/dataloaders.py
+7
-10
general.py
utils/general.py
+1
-1
__init__.py
utils/loggers/__init__.py
+2
-2
metrics.py
utils/metrics.py
+20
-21
torch_utils.py
utils/torch_utils.py
+13
-14
没有找到文件。
detect.py
浏览文件 @
f0007141
...
@@ -160,15 +160,15 @@ def run(
...
@@ -160,15 +160,15 @@ def run(
if
save_txt
:
# Write to file
if
save_txt
:
# Write to file
xywh
=
(
xyxy2xywh
(
torch
.
tensor
(
xyxy
)
.
view
(
1
,
4
))
/
gn
)
.
view
(
-
1
)
.
tolist
()
# normalized xywh
xywh
=
(
xyxy2xywh
(
torch
.
tensor
(
xyxy
)
.
view
(
1
,
4
))
/
gn
)
.
view
(
-
1
)
.
tolist
()
# normalized xywh
line
=
(
cls
,
*
xywh
,
conf
)
if
save_conf
else
(
cls
,
*
xywh
)
# label format
line
=
(
cls
,
*
xywh
,
conf
)
if
save_conf
else
(
cls
,
*
xywh
)
# label format
with
open
(
txt_path
+
'
.txt'
,
'a'
)
as
f
:
with
open
(
f
'{txt_path}
.txt'
,
'a'
)
as
f
:
f
.
write
((
'
%
g '
*
len
(
line
))
.
rstrip
()
%
line
+
'
\n
'
)
f
.
write
((
'
%
g '
*
len
(
line
))
.
rstrip
()
%
line
+
'
\n
'
)
if
save_img
or
save_crop
or
view_img
:
# Add bbox to image
if
save_img
or
save_crop
or
view_img
:
# Add bbox to image
c
=
int
(
cls
)
# integer class
c
=
int
(
cls
)
# integer class
label
=
None
if
hide_labels
else
(
names
[
c
]
if
hide_conf
else
f
'{names[c]} {conf:.2f}'
)
label
=
None
if
hide_labels
else
(
names
[
c
]
if
hide_conf
else
f
'{names[c]} {conf:.2f}'
)
annotator
.
box_label
(
xyxy
,
label
,
color
=
colors
(
c
,
True
))
annotator
.
box_label
(
xyxy
,
label
,
color
=
colors
(
c
,
True
))
if
save_crop
:
if
save_crop
:
save_one_box
(
xyxy
,
imc
,
file
=
save_dir
/
'crops'
/
names
[
c
]
/
f
'{p.stem}.jpg'
,
BGR
=
True
)
save_one_box
(
xyxy
,
imc
,
file
=
save_dir
/
'crops'
/
names
[
c
]
/
f
'{p.stem}.jpg'
,
BGR
=
True
)
# Stream results
# Stream results
im0
=
annotator
.
result
()
im0
=
annotator
.
result
()
...
...
export.py
浏览文件 @
f0007141
...
@@ -175,7 +175,7 @@ def export_openvino(model, im, file, half, prefix=colorstr('OpenVINO:')):
...
@@ -175,7 +175,7 @@ def export_openvino(model, im, file, half, prefix=colorstr('OpenVINO:')):
import
openvino.inference_engine
as
ie
import
openvino.inference_engine
as
ie
LOGGER
.
info
(
f
'
\n
{prefix} starting export with openvino {ie.__version__}...'
)
LOGGER
.
info
(
f
'
\n
{prefix} starting export with openvino {ie.__version__}...'
)
f
=
str
(
file
)
.
replace
(
'.pt'
,
'_openvino_model'
+
os
.
sep
)
f
=
str
(
file
)
.
replace
(
'.pt'
,
f
'_openvino_model{os.sep}'
)
cmd
=
f
"mo --input_model {file.with_suffix('.onnx')} --output_dir {f} --data_type {'FP16' if half else 'FP32'}"
cmd
=
f
"mo --input_model {file.with_suffix('.onnx')} --output_dir {f} --data_type {'FP16' if half else 'FP32'}"
subprocess
.
check_output
(
cmd
,
shell
=
True
)
subprocess
.
check_output
(
cmd
,
shell
=
True
)
...
@@ -385,7 +385,7 @@ def export_edgetpu(keras_model, im, file, prefix=colorstr('Edge TPU:')):
...
@@ -385,7 +385,7 @@ def export_edgetpu(keras_model, im, file, prefix=colorstr('Edge TPU:')):
cmd
=
'edgetpu_compiler --version'
cmd
=
'edgetpu_compiler --version'
help_url
=
'https://coral.ai/docs/edgetpu/compiler/'
help_url
=
'https://coral.ai/docs/edgetpu/compiler/'
assert
platform
.
system
()
==
'Linux'
,
f
'export only supported on Linux. See {help_url}'
assert
platform
.
system
()
==
'Linux'
,
f
'export only supported on Linux. See {help_url}'
if
subprocess
.
run
(
cmd
+
'
>/dev/null'
,
shell
=
True
)
.
returncode
!=
0
:
if
subprocess
.
run
(
f
'{cmd}
>/dev/null'
,
shell
=
True
)
.
returncode
!=
0
:
LOGGER
.
info
(
f
'
\n
{prefix} export requires Edge TPU compiler. Attempting install from {help_url}'
)
LOGGER
.
info
(
f
'
\n
{prefix} export requires Edge TPU compiler. Attempting install from {help_url}'
)
sudo
=
subprocess
.
run
(
'sudo --version >/dev/null'
,
shell
=
True
)
.
returncode
==
0
# sudo installed on system
sudo
=
subprocess
.
run
(
'sudo --version >/dev/null'
,
shell
=
True
)
.
returncode
==
0
# sudo installed on system
for
c
in
(
for
c
in
(
...
@@ -419,7 +419,7 @@ def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
...
@@ -419,7 +419,7 @@ def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
LOGGER
.
info
(
f
'
\n
{prefix} starting export with tensorflowjs {tfjs.__version__}...'
)
LOGGER
.
info
(
f
'
\n
{prefix} starting export with tensorflowjs {tfjs.__version__}...'
)
f
=
str
(
file
)
.
replace
(
'.pt'
,
'_web_model'
)
# js dir
f
=
str
(
file
)
.
replace
(
'.pt'
,
'_web_model'
)
# js dir
f_pb
=
file
.
with_suffix
(
'.pb'
)
# *.pb path
f_pb
=
file
.
with_suffix
(
'.pb'
)
# *.pb path
f_json
=
f
+
'
/model.json'
# *.json path
f_json
=
f
'{f}
/model.json'
# *.json path
cmd
=
f
'tensorflowjs_converter --input_format=tf_frozen_model '
\
cmd
=
f
'tensorflowjs_converter --input_format=tf_frozen_model '
\
f
'--output_node_names="Identity,Identity_1,Identity_2,Identity_3" {f_pb} {f}'
f
'--output_node_names="Identity,Identity_1,Identity_2,Identity_3" {f_pb} {f}'
...
...
train.py
浏览文件 @
f0007141
...
@@ -88,7 +88,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
...
@@ -88,7 +88,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Loggers
# Loggers
data_dict
=
None
data_dict
=
None
if
RANK
in
[
-
1
,
0
]
:
if
RANK
in
{
-
1
,
0
}
:
loggers
=
Loggers
(
save_dir
,
weights
,
opt
,
hyp
,
LOGGER
)
# loggers instance
loggers
=
Loggers
(
save_dir
,
weights
,
opt
,
hyp
,
LOGGER
)
# loggers instance
if
loggers
.
wandb
:
if
loggers
.
wandb
:
data_dict
=
loggers
.
wandb
.
data_dict
data_dict
=
loggers
.
wandb
.
data_dict
...
@@ -181,7 +181,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
...
@@ -181,7 +181,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
scheduler
=
lr_scheduler
.
LambdaLR
(
optimizer
,
lr_lambda
=
lf
)
# plot_lr_scheduler(optimizer, scheduler, epochs)
scheduler
=
lr_scheduler
.
LambdaLR
(
optimizer
,
lr_lambda
=
lf
)
# plot_lr_scheduler(optimizer, scheduler, epochs)
# EMA
# EMA
ema
=
ModelEMA
(
model
)
if
RANK
in
[
-
1
,
0
]
else
None
ema
=
ModelEMA
(
model
)
if
RANK
in
{
-
1
,
0
}
else
None
# Resume
# Resume
start_epoch
,
best_fitness
=
0
,
0.0
start_epoch
,
best_fitness
=
0
,
0.0
...
@@ -238,7 +238,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
...
@@ -238,7 +238,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
assert
mlc
<
nc
,
f
'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'
assert
mlc
<
nc
,
f
'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'
# Process 0
# Process 0
if
RANK
in
[
-
1
,
0
]
:
if
RANK
in
{
-
1
,
0
}
:
val_loader
=
create_dataloader
(
val_path
,
val_loader
=
create_dataloader
(
val_path
,
imgsz
,
imgsz
,
batch_size
//
WORLD_SIZE
*
2
,
batch_size
//
WORLD_SIZE
*
2
,
...
@@ -320,7 +320,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
...
@@ -320,7 +320,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
train_loader
.
sampler
.
set_epoch
(
epoch
)
train_loader
.
sampler
.
set_epoch
(
epoch
)
pbar
=
enumerate
(
train_loader
)
pbar
=
enumerate
(
train_loader
)
LOGGER
.
info
((
'
\n
'
+
'
%10
s'
*
7
)
%
(
'Epoch'
,
'gpu_mem'
,
'box'
,
'obj'
,
'cls'
,
'labels'
,
'img_size'
))
LOGGER
.
info
((
'
\n
'
+
'
%10
s'
*
7
)
%
(
'Epoch'
,
'gpu_mem'
,
'box'
,
'obj'
,
'cls'
,
'labels'
,
'img_size'
))
if
RANK
in
(
-
1
,
0
)
:
if
RANK
in
{
-
1
,
0
}
:
pbar
=
tqdm
(
pbar
,
total
=
nb
,
bar_format
=
'{l_bar}{bar:10}{r_bar}{bar:-10b}'
)
# progress bar
pbar
=
tqdm
(
pbar
,
total
=
nb
,
bar_format
=
'{l_bar}{bar:10}{r_bar}{bar:-10b}'
)
# progress bar
optimizer
.
zero_grad
()
optimizer
.
zero_grad
()
for
i
,
(
imgs
,
targets
,
paths
,
_
)
in
pbar
:
# batch -------------------------------------------------------------
for
i
,
(
imgs
,
targets
,
paths
,
_
)
in
pbar
:
# batch -------------------------------------------------------------
...
@@ -369,7 +369,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
...
@@ -369,7 +369,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
last_opt_step
=
ni
last_opt_step
=
ni
# Log
# Log
if
RANK
in
(
-
1
,
0
)
:
if
RANK
in
{
-
1
,
0
}
:
mloss
=
(
mloss
*
i
+
loss_items
)
/
(
i
+
1
)
# update mean losses
mloss
=
(
mloss
*
i
+
loss_items
)
/
(
i
+
1
)
# update mean losses
mem
=
f
'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G'
# (GB)
mem
=
f
'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G'
# (GB)
pbar
.
set_description
((
'
%10
s'
*
2
+
'
%10.4
g'
*
5
)
%
pbar
.
set_description
((
'
%10
s'
*
2
+
'
%10.4
g'
*
5
)
%
...
@@ -383,7 +383,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
...
@@ -383,7 +383,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
lr
=
[
x
[
'lr'
]
for
x
in
optimizer
.
param_groups
]
# for loggers
lr
=
[
x
[
'lr'
]
for
x
in
optimizer
.
param_groups
]
# for loggers
scheduler
.
step
()
scheduler
.
step
()
if
RANK
in
(
-
1
,
0
)
:
if
RANK
in
{
-
1
,
0
}
:
# mAP
# mAP
callbacks
.
run
(
'on_train_epoch_end'
,
epoch
=
epoch
)
callbacks
.
run
(
'on_train_epoch_end'
,
epoch
=
epoch
)
ema
.
update_attr
(
model
,
include
=
[
'yaml'
,
'nc'
,
'hyp'
,
'names'
,
'stride'
,
'class_weights'
])
ema
.
update_attr
(
model
,
include
=
[
'yaml'
,
'nc'
,
'hyp'
,
'names'
,
'stride'
,
'class_weights'
])
...
@@ -444,7 +444,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
...
@@ -444,7 +444,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# end epoch ----------------------------------------------------------------------------------------------------
# end epoch ----------------------------------------------------------------------------------------------------
# end training -----------------------------------------------------------------------------------------------------
# end training -----------------------------------------------------------------------------------------------------
if
RANK
in
(
-
1
,
0
)
:
if
RANK
in
{
-
1
,
0
}
:
LOGGER
.
info
(
f
'
\n
{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.'
)
LOGGER
.
info
(
f
'
\n
{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.'
)
for
f
in
last
,
best
:
for
f
in
last
,
best
:
if
f
.
exists
():
if
f
.
exists
():
...
@@ -522,7 +522,7 @@ def parse_opt(known=False):
...
@@ -522,7 +522,7 @@ def parse_opt(known=False):
def
main
(
opt
,
callbacks
=
Callbacks
()):
def
main
(
opt
,
callbacks
=
Callbacks
()):
# Checks
# Checks
if
RANK
in
(
-
1
,
0
)
:
if
RANK
in
{
-
1
,
0
}
:
print_args
(
vars
(
opt
))
print_args
(
vars
(
opt
))
check_git_status
()
check_git_status
()
check_requirements
(
exclude
=
[
'thop'
])
check_requirements
(
exclude
=
[
'thop'
])
...
...
utils/autoanchor.py
浏览文件 @
f0007141
...
@@ -104,7 +104,7 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
...
@@ -104,7 +104,7 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
s
=
f
'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr
\n
'
\
s
=
f
'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr
\n
'
\
f
'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
\
f
'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
\
f
'past_thr={x[x > thr].mean():.3f}-mean: '
f
'past_thr={x[x > thr].mean():.3f}-mean: '
for
i
,
x
in
enumerate
(
k
)
:
for
x
in
k
:
s
+=
'
%
i,
%
i, '
%
(
round
(
x
[
0
]),
round
(
x
[
1
]))
s
+=
'
%
i,
%
i, '
%
(
round
(
x
[
0
]),
round
(
x
[
1
]))
if
verbose
:
if
verbose
:
LOGGER
.
info
(
s
[:
-
2
])
LOGGER
.
info
(
s
[:
-
2
])
...
...
utils/dataloaders.py
浏览文件 @
f0007141
...
@@ -57,9 +57,7 @@ def exif_size(img):
...
@@ -57,9 +57,7 @@ def exif_size(img):
s
=
img
.
size
# (width, height)
s
=
img
.
size
# (width, height)
try
:
try
:
rotation
=
dict
(
img
.
_getexif
()
.
items
())[
orientation
]
rotation
=
dict
(
img
.
_getexif
()
.
items
())[
orientation
]
if
rotation
==
6
:
# rotation 270
if
rotation
in
[
6
,
8
]:
# rotation 270 or 90
s
=
(
s
[
1
],
s
[
0
])
elif
rotation
==
8
:
# rotation 90
s
=
(
s
[
1
],
s
[
0
])
s
=
(
s
[
1
],
s
[
0
])
except
Exception
:
except
Exception
:
pass
pass
...
@@ -156,7 +154,7 @@ class InfiniteDataLoader(dataloader.DataLoader):
...
@@ -156,7 +154,7 @@ class InfiniteDataLoader(dataloader.DataLoader):
return
len
(
self
.
batch_sampler
.
sampler
)
return
len
(
self
.
batch_sampler
.
sampler
)
def
__iter__
(
self
):
def
__iter__
(
self
):
for
i
in
range
(
len
(
self
)):
for
_
in
range
(
len
(
self
)):
yield
next
(
self
.
iterator
)
yield
next
(
self
.
iterator
)
...
@@ -224,10 +222,9 @@ class LoadImages:
...
@@ -224,10 +222,9 @@ class LoadImages:
self
.
cap
.
release
()
self
.
cap
.
release
()
if
self
.
count
==
self
.
nf
:
# last video
if
self
.
count
==
self
.
nf
:
# last video
raise
StopIteration
raise
StopIteration
else
:
path
=
self
.
files
[
self
.
count
]
path
=
self
.
files
[
self
.
count
]
self
.
new_video
(
path
)
self
.
new_video
(
path
)
ret_val
,
img0
=
self
.
cap
.
read
()
ret_val
,
img0
=
self
.
cap
.
read
()
self
.
frame
+=
1
self
.
frame
+=
1
s
=
f
'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
s
=
f
'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
...
@@ -390,7 +387,7 @@ class LoadStreams:
...
@@ -390,7 +387,7 @@ class LoadStreams:
def
img2label_paths
(
img_paths
):
def
img2label_paths
(
img_paths
):
# Define label paths as a function of image paths
# Define label paths as a function of image paths
sa
,
sb
=
os
.
sep
+
'images'
+
os
.
sep
,
os
.
sep
+
'labels'
+
os
.
sep
# /images/, /labels/ substrings
sa
,
sb
=
f
'{os.sep}images{os.sep}'
,
f
'{os.sep}labels{os.sep}'
# /images/, /labels/ substrings
return
[
sb
.
join
(
x
.
rsplit
(
sa
,
1
))
.
rsplit
(
'.'
,
1
)[
0
]
+
'.txt'
for
x
in
img_paths
]
return
[
sb
.
join
(
x
.
rsplit
(
sa
,
1
))
.
rsplit
(
'.'
,
1
)[
0
]
+
'.txt'
for
x
in
img_paths
]
...
@@ -456,7 +453,7 @@ class LoadImagesAndLabels(Dataset):
...
@@ -456,7 +453,7 @@ class LoadImagesAndLabels(Dataset):
# Display cache
# Display cache
nf
,
nm
,
ne
,
nc
,
n
=
cache
.
pop
(
'results'
)
# found, missing, empty, corrupt, total
nf
,
nm
,
ne
,
nc
,
n
=
cache
.
pop
(
'results'
)
# found, missing, empty, corrupt, total
if
exists
and
LOCAL_RANK
in
(
-
1
,
0
)
:
if
exists
and
LOCAL_RANK
in
{
-
1
,
0
}
:
d
=
f
"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupt"
d
=
f
"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupt"
tqdm
(
None
,
desc
=
prefix
+
d
,
total
=
n
,
initial
=
n
,
bar_format
=
BAR_FORMAT
)
# display cache results
tqdm
(
None
,
desc
=
prefix
+
d
,
total
=
n
,
initial
=
n
,
bar_format
=
BAR_FORMAT
)
# display cache results
if
cache
[
'msgs'
]:
if
cache
[
'msgs'
]:
...
...
utils/general.py
浏览文件 @
f0007141
...
@@ -84,7 +84,7 @@ def set_logging(name=None, verbose=VERBOSE):
...
@@ -84,7 +84,7 @@ def set_logging(name=None, verbose=VERBOSE):
for
h
in
logging
.
root
.
handlers
:
for
h
in
logging
.
root
.
handlers
:
logging
.
root
.
removeHandler
(
h
)
# remove all handlers associated with the root logger object
logging
.
root
.
removeHandler
(
h
)
# remove all handlers associated with the root logger object
rank
=
int
(
os
.
getenv
(
'RANK'
,
-
1
))
# rank in world for Multi-GPU trainings
rank
=
int
(
os
.
getenv
(
'RANK'
,
-
1
))
# rank in world for Multi-GPU trainings
level
=
logging
.
INFO
if
(
verbose
and
rank
in
(
-
1
,
0
))
else
logging
.
WARNING
level
=
logging
.
INFO
if
verbose
and
rank
in
{
-
1
,
0
}
else
logging
.
WARNING
log
=
logging
.
getLogger
(
name
)
log
=
logging
.
getLogger
(
name
)
log
.
setLevel
(
level
)
log
.
setLevel
(
level
)
handler
=
logging
.
StreamHandler
()
handler
=
logging
.
StreamHandler
()
...
...
utils/loggers/__init__.py
浏览文件 @
f0007141
...
@@ -22,7 +22,7 @@ try:
...
@@ -22,7 +22,7 @@ try:
import
wandb
import
wandb
assert
hasattr
(
wandb
,
'__version__'
)
# verify package import not local dir
assert
hasattr
(
wandb
,
'__version__'
)
# verify package import not local dir
if
pkg
.
parse_version
(
wandb
.
__version__
)
>=
pkg
.
parse_version
(
'0.12.2'
)
and
RANK
in
[
0
,
-
1
]
:
if
pkg
.
parse_version
(
wandb
.
__version__
)
>=
pkg
.
parse_version
(
'0.12.2'
)
and
RANK
in
{
0
,
-
1
}
:
try
:
try
:
wandb_login_success
=
wandb
.
login
(
timeout
=
30
)
wandb_login_success
=
wandb
.
login
(
timeout
=
30
)
except
wandb
.
errors
.
UsageError
:
# known non-TTY terminal issue
except
wandb
.
errors
.
UsageError
:
# known non-TTY terminal issue
...
@@ -176,7 +176,7 @@ class Loggers():
...
@@ -176,7 +176,7 @@ class Loggers():
if
not
self
.
opt
.
evolve
:
if
not
self
.
opt
.
evolve
:
wandb
.
log_artifact
(
str
(
best
if
best
.
exists
()
else
last
),
wandb
.
log_artifact
(
str
(
best
if
best
.
exists
()
else
last
),
type
=
'model'
,
type
=
'model'
,
name
=
'run_'
+
self
.
wandb
.
wandb_run
.
id
+
'
_model'
,
name
=
f
'run_{self.wandb.wandb_run.id}
_model'
,
aliases
=
[
'latest'
,
'best'
,
'stripped'
])
aliases
=
[
'latest'
,
'best'
,
'stripped'
])
self
.
wandb
.
finish_run
()
self
.
wandb
.
finish_run
()
...
...
utils/metrics.py
浏览文件 @
f0007141
...
@@ -55,32 +55,31 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names
...
@@ -55,32 +55,31 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names
i
=
pred_cls
==
c
i
=
pred_cls
==
c
n_l
=
nt
[
ci
]
# number of labels
n_l
=
nt
[
ci
]
# number of labels
n_p
=
i
.
sum
()
# number of predictions
n_p
=
i
.
sum
()
# number of predictions
if
n_p
==
0
or
n_l
==
0
:
if
n_p
==
0
or
n_l
==
0
:
continue
continue
else
:
# Accumulate FPs and TPs
fpc
=
(
1
-
tp
[
i
])
.
cumsum
(
0
)
tpc
=
tp
[
i
]
.
cumsum
(
0
)
# Recall
# Accumulate FPs and TPs
recall
=
tpc
/
(
n_l
+
eps
)
# recall curve
fpc
=
(
1
-
tp
[
i
])
.
cumsum
(
0
)
r
[
ci
]
=
np
.
interp
(
-
px
,
-
conf
[
i
],
recall
[:,
0
],
left
=
0
)
# negative x, xp because xp decreases
tpc
=
tp
[
i
]
.
cumsum
(
0
)
# Recall
recall
=
tpc
/
(
n_l
+
eps
)
# recall curve
r
[
ci
]
=
np
.
interp
(
-
px
,
-
conf
[
i
],
recall
[:,
0
],
left
=
0
)
# negative x, xp because xp decreases
# Precision
# Precision
precision
=
tpc
/
(
tpc
+
fpc
)
# precision curve
precision
=
tpc
/
(
tpc
+
fpc
)
# precision curve
p
[
ci
]
=
np
.
interp
(
-
px
,
-
conf
[
i
],
precision
[:,
0
],
left
=
1
)
# p at pr_score
p
[
ci
]
=
np
.
interp
(
-
px
,
-
conf
[
i
],
precision
[:,
0
],
left
=
1
)
# p at pr_score
# AP from recall-precision curve
# AP from recall-precision curve
for
j
in
range
(
tp
.
shape
[
1
]):
for
j
in
range
(
tp
.
shape
[
1
]):
ap
[
ci
,
j
],
mpre
,
mrec
=
compute_ap
(
recall
[:,
j
],
precision
[:,
j
])
ap
[
ci
,
j
],
mpre
,
mrec
=
compute_ap
(
recall
[:,
j
],
precision
[:,
j
])
if
plot
and
j
==
0
:
if
plot
and
j
==
0
:
py
.
append
(
np
.
interp
(
px
,
mrec
,
mpre
))
# precision at mAP@0.5
py
.
append
(
np
.
interp
(
px
,
mrec
,
mpre
))
# precision at mAP@0.5
# Compute F1 (harmonic mean of precision and recall)
# Compute F1 (harmonic mean of precision and recall)
f1
=
2
*
p
*
r
/
(
p
+
r
+
eps
)
f1
=
2
*
p
*
r
/
(
p
+
r
+
eps
)
names
=
[
v
for
k
,
v
in
names
.
items
()
if
k
in
unique_classes
]
# list: only classes that have data
names
=
[
v
for
k
,
v
in
names
.
items
()
if
k
in
unique_classes
]
# list: only classes that have data
names
=
{
i
:
v
for
i
,
v
in
enumerate
(
names
)}
# to dict
names
=
dict
(
enumerate
(
names
))
# to dict
if
plot
:
if
plot
:
plot_pr_curve
(
px
,
py
,
ap
,
Path
(
save_dir
)
/
'PR_curve.png'
,
names
)
plot_pr_curve
(
px
,
py
,
ap
,
Path
(
save_dir
)
/
'PR_curve.png'
,
names
)
plot_mc_curve
(
px
,
f1
,
Path
(
save_dir
)
/
'F1_curve.png'
,
names
,
ylabel
=
'F1'
)
plot_mc_curve
(
px
,
f1
,
Path
(
save_dir
)
/
'F1_curve.png'
,
names
,
ylabel
=
'F1'
)
...
@@ -314,7 +313,7 @@ def wh_iou(wh1, wh2):
...
@@ -314,7 +313,7 @@ def wh_iou(wh1, wh2):
# Plots ----------------------------------------------------------------------------------------------------------------
# Plots ----------------------------------------------------------------------------------------------------------------
def
plot_pr_curve
(
px
,
py
,
ap
,
save_dir
=
'pr_curve.png'
,
names
=
()):
def
plot_pr_curve
(
px
,
py
,
ap
,
save_dir
=
Path
(
'pr_curve.png'
)
,
names
=
()):
# Precision-recall curve
# Precision-recall curve
fig
,
ax
=
plt
.
subplots
(
1
,
1
,
figsize
=
(
9
,
6
),
tight_layout
=
True
)
fig
,
ax
=
plt
.
subplots
(
1
,
1
,
figsize
=
(
9
,
6
),
tight_layout
=
True
)
py
=
np
.
stack
(
py
,
axis
=
1
)
py
=
np
.
stack
(
py
,
axis
=
1
)
...
@@ -331,11 +330,11 @@ def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
...
@@ -331,11 +330,11 @@ def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
ax
.
set_xlim
(
0
,
1
)
ax
.
set_xlim
(
0
,
1
)
ax
.
set_ylim
(
0
,
1
)
ax
.
set_ylim
(
0
,
1
)
plt
.
legend
(
bbox_to_anchor
=
(
1.04
,
1
),
loc
=
"upper left"
)
plt
.
legend
(
bbox_to_anchor
=
(
1.04
,
1
),
loc
=
"upper left"
)
fig
.
savefig
(
Path
(
save_dir
)
,
dpi
=
250
)
fig
.
savefig
(
save_dir
,
dpi
=
250
)
plt
.
close
()
plt
.
close
()
def
plot_mc_curve
(
px
,
py
,
save_dir
=
'mc_curve.png'
,
names
=
(),
xlabel
=
'Confidence'
,
ylabel
=
'Metric'
):
def
plot_mc_curve
(
px
,
py
,
save_dir
=
Path
(
'mc_curve.png'
)
,
names
=
(),
xlabel
=
'Confidence'
,
ylabel
=
'Metric'
):
# Metric-confidence curve
# Metric-confidence curve
fig
,
ax
=
plt
.
subplots
(
1
,
1
,
figsize
=
(
9
,
6
),
tight_layout
=
True
)
fig
,
ax
=
plt
.
subplots
(
1
,
1
,
figsize
=
(
9
,
6
),
tight_layout
=
True
)
...
@@ -352,5 +351,5 @@ def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence'
...
@@ -352,5 +351,5 @@ def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence'
ax
.
set_xlim
(
0
,
1
)
ax
.
set_xlim
(
0
,
1
)
ax
.
set_ylim
(
0
,
1
)
ax
.
set_ylim
(
0
,
1
)
plt
.
legend
(
bbox_to_anchor
=
(
1.04
,
1
),
loc
=
"upper left"
)
plt
.
legend
(
bbox_to_anchor
=
(
1.04
,
1
),
loc
=
"upper left"
)
fig
.
savefig
(
Path
(
save_dir
)
,
dpi
=
250
)
fig
.
savefig
(
save_dir
,
dpi
=
250
)
plt
.
close
()
plt
.
close
()
utils/torch_utils.py
浏览文件 @
f0007141
...
@@ -50,9 +50,9 @@ def device_count():
...
@@ -50,9 +50,9 @@ def device_count():
def
select_device
(
device
=
''
,
batch_size
=
0
,
newline
=
True
):
def
select_device
(
device
=
''
,
batch_size
=
0
,
newline
=
True
):
# device =
'cpu'
or '0' or '0,1,2,3'
# device =
None or 'cpu' or 0
or '0' or '0,1,2,3'
s
=
f
'YOLOv5 🚀 {git_describe() or file_date()} Python-{platform.python_version()} torch-{torch.__version__} '
s
=
f
'YOLOv5 🚀 {git_describe() or file_date()} Python-{platform.python_version()} torch-{torch.__version__} '
device
=
str
(
device
)
.
strip
()
.
lower
()
.
replace
(
'cuda:'
,
''
)
# to string, 'cuda:0' to '0'
device
=
str
(
device
)
.
strip
()
.
lower
()
.
replace
(
'cuda:'
,
''
)
.
replace
(
'none'
,
''
)
# to string, 'cuda:0' to '0'
cpu
=
device
==
'cpu'
cpu
=
device
==
'cpu'
if
cpu
:
if
cpu
:
os
.
environ
[
'CUDA_VISIBLE_DEVICES'
]
=
'-1'
# force torch.cuda.is_available() = False
os
.
environ
[
'CUDA_VISIBLE_DEVICES'
]
=
'-1'
# force torch.cuda.is_available() = False
...
@@ -97,7 +97,8 @@ def profile(input, ops, n=10, device=None):
...
@@ -97,7 +97,8 @@ def profile(input, ops, n=10, device=None):
# profile(input, [m1, m2], n=100) # profile over 100 iterations
# profile(input, [m1, m2], n=100) # profile over 100 iterations
results
=
[]
results
=
[]
device
=
device
or
select_device
()
if
not
isinstance
(
device
,
torch
.
device
):
device
=
select_device
(
device
)
print
(
f
"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}"
print
(
f
"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}"
f
"{'input':>24s}{'output':>24s}"
)
f
"{'input':>24s}{'output':>24s}"
)
...
@@ -127,9 +128,8 @@ def profile(input, ops, n=10, device=None):
...
@@ -127,9 +128,8 @@ def profile(input, ops, n=10, device=None):
tf
+=
(
t
[
1
]
-
t
[
0
])
*
1000
/
n
# ms per op forward
tf
+=
(
t
[
1
]
-
t
[
0
])
*
1000
/
n
# ms per op forward
tb
+=
(
t
[
2
]
-
t
[
1
])
*
1000
/
n
# ms per op backward
tb
+=
(
t
[
2
]
-
t
[
1
])
*
1000
/
n
# ms per op backward
mem
=
torch
.
cuda
.
memory_reserved
()
/
1E9
if
torch
.
cuda
.
is_available
()
else
0
# (GB)
mem
=
torch
.
cuda
.
memory_reserved
()
/
1E9
if
torch
.
cuda
.
is_available
()
else
0
# (GB)
s_in
=
tuple
(
x
.
shape
)
if
isinstance
(
x
,
torch
.
Tensor
)
else
'list'
s_in
,
s_out
=
(
tuple
(
x
.
shape
)
if
isinstance
(
x
,
torch
.
Tensor
)
else
'list'
for
x
in
(
x
,
y
))
# shapes
s_out
=
tuple
(
y
.
shape
)
if
isinstance
(
y
,
torch
.
Tensor
)
else
'list'
p
=
sum
(
x
.
numel
()
for
x
in
m
.
parameters
())
if
isinstance
(
m
,
nn
.
Module
)
else
0
# parameters
p
=
sum
(
list
(
x
.
numel
()
for
x
in
m
.
parameters
()))
if
isinstance
(
m
,
nn
.
Module
)
else
0
# parameters
print
(
f
'{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}'
)
print
(
f
'{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}'
)
results
.
append
([
p
,
flops
,
mem
,
tf
,
tb
,
s_in
,
s_out
])
results
.
append
([
p
,
flops
,
mem
,
tf
,
tb
,
s_in
,
s_out
])
except
Exception
as
e
:
except
Exception
as
e
:
...
@@ -227,7 +227,7 @@ def model_info(model, verbose=False, img_size=640):
...
@@ -227,7 +227,7 @@ def model_info(model, verbose=False, img_size=640):
flops
=
profile
(
deepcopy
(
model
),
inputs
=
(
img
,),
verbose
=
False
)[
0
]
/
1E9
*
2
# stride GFLOPs
flops
=
profile
(
deepcopy
(
model
),
inputs
=
(
img
,),
verbose
=
False
)[
0
]
/
1E9
*
2
# stride GFLOPs
img_size
=
img_size
if
isinstance
(
img_size
,
list
)
else
[
img_size
,
img_size
]
# expand if int/float
img_size
=
img_size
if
isinstance
(
img_size
,
list
)
else
[
img_size
,
img_size
]
# expand if int/float
fs
=
',
%.1
f GFLOPs'
%
(
flops
*
img_size
[
0
]
/
stride
*
img_size
[
1
]
/
stride
)
# 640x640 GFLOPs
fs
=
',
%.1
f GFLOPs'
%
(
flops
*
img_size
[
0
]
/
stride
*
img_size
[
1
]
/
stride
)
# 640x640 GFLOPs
except
(
ImportError
,
Exception
)
:
except
Exception
:
fs
=
''
fs
=
''
name
=
Path
(
model
.
yaml_file
)
.
stem
.
replace
(
'yolov5'
,
'YOLOv5'
)
if
hasattr
(
model
,
'yaml_file'
)
else
'Model'
name
=
Path
(
model
.
yaml_file
)
.
stem
.
replace
(
'yolov5'
,
'YOLOv5'
)
if
hasattr
(
model
,
'yaml_file'
)
else
'Model'
...
@@ -238,13 +238,12 @@ def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
...
@@ -238,13 +238,12 @@ def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
# Scales img(bs,3,y,x) by ratio constrained to gs-multiple
# Scales img(bs,3,y,x) by ratio constrained to gs-multiple
if
ratio
==
1.0
:
if
ratio
==
1.0
:
return
img
return
img
else
:
h
,
w
=
img
.
shape
[
2
:]
h
,
w
=
img
.
shape
[
2
:]
s
=
(
int
(
h
*
ratio
),
int
(
w
*
ratio
))
# new size
s
=
(
int
(
h
*
ratio
),
int
(
w
*
ratio
))
# new size
img
=
F
.
interpolate
(
img
,
size
=
s
,
mode
=
'bilinear'
,
align_corners
=
False
)
# resize
img
=
F
.
interpolate
(
img
,
size
=
s
,
mode
=
'bilinear'
,
align_corners
=
False
)
# resize
if
not
same_shape
:
# pad/crop img
if
not
same_shape
:
# pad/crop img
h
,
w
=
(
math
.
ceil
(
x
*
ratio
/
gs
)
*
gs
for
x
in
(
h
,
w
))
h
,
w
=
(
math
.
ceil
(
x
*
ratio
/
gs
)
*
gs
for
x
in
(
h
,
w
))
return
F
.
pad
(
img
,
[
0
,
w
-
s
[
1
],
0
,
h
-
s
[
0
]],
value
=
0.447
)
# value = imagenet mean
return
F
.
pad
(
img
,
[
0
,
w
-
s
[
1
],
0
,
h
-
s
[
0
]],
value
=
0.447
)
# value = imagenet mean
def
copy_attr
(
a
,
b
,
include
=
(),
exclude
=
()):
def
copy_attr
(
a
,
b
,
include
=
(),
exclude
=
()):
...
...
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