Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
S
simple-yolov3-benchmark
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Weihao KONG
simple-yolov3-benchmark
Commits
8154b9bb
Commit
8154b9bb
authored
Jul 26, 2021
by
Weihao KONG
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Remove non-parallel old script
parent
66978061
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
102 additions
and
253 deletions
+102
-253
run_benchmark.py
+102
-100
run_benchmark_parallel.py
+0
-153
No files found.
run_benchmark.py
View file @
8154b9bb
...
...
@@ -8,6 +8,7 @@ parser.add_argument('--gpu',dest='gpu',action='store_true',help='Whether to use
parser
.
add_argument
(
'--dla1'
,
dest
=
'dla1'
,
action
=
'store_true'
,
help
=
'Whether to use DLA core 1 for inference'
)
parser
.
add_argument
(
'--dla2'
,
dest
=
'dla2'
,
action
=
'store_true'
,
help
=
'Whether to use DLA core 2 for inference'
)
parser
.
add_argument
(
'--bs'
,
dest
=
'bs'
,
type
=
int
,
default
=
1
,
help
=
'Batch size of inference'
)
parser
.
add_argument
(
'--parallelruns'
,
dest
=
'parallelruns'
,
type
=
int
,
default
=
1
,
help
=
'Processes launched in parallel for each device'
)
args
=
parser
.
parse_args
()
...
...
@@ -39,113 +40,114 @@ def gen_command(onnx_path, engine_path, useDLACore):
return
run_command
processes
=
{
'gpu'
:
None
,
'dla1'
:
None
,
'dla2'
:
None
'gpu'
:
[]
,
'dla1'
:
[]
,
'dla2'
:
[]
}
logfiles
=
{
'gpu'
:
None
,
'dla1'
:
None
,
'dla2'
:
None
'gpu'
:
[]
,
'dla1'
:
[]
,
'dla2'
:
[]
}
if
args
.
gpu
:
print
(
'Launching GPU process'
)
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_gpu.stdout'
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_gpu.stderr'
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'gpu.engine'
),
useDLACore
=
None
)
processes
[
'gpu'
]
=
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
)
logfiles
[
'gpu'
]
=
(
f_stdout
,
f_stderr
)
if
args
.
dla1
:
print
(
'Launching DLA1 process'
)
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla1.stdout'
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla1.stderr'
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'dla1.engine'
),
useDLACore
=
0
)
processes
[
'dla1'
]
=
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
)
logfiles
[
'dla1'
]
=
(
f_stdout
,
f_stderr
)
if
args
.
dla2
:
print
(
'Launching DLA2 process'
)
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla2.stdout'
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla2.stderr'
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'dla2.engine'
),
useDLACore
=
1
)
processes
[
'dla2'
]
=
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
)
logfiles
[
'dla2'
]
=
(
f_stdout
,
f_stderr
)
for
process
in
processes
.
values
():
if
process
==
None
:
for
i
in
range
(
args
.
parallelruns
):
if
args
.
gpu
:
print
(
'Launching GPU process {:d}'
.
format
(
i
))
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_gpu.stdout.{:d}'
.
format
(
i
)
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_gpu.stderr.{:d}'
.
format
(
i
)
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'gpu.engine'
),
useDLACore
=
None
)
processes
[
'gpu'
]
.
append
(
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
))
logfiles
[
'gpu'
]
.
append
((
f_stdout
,
f_stderr
))
if
args
.
dla1
:
print
(
'Launching DLA1 process {:d}'
.
format
(
i
))
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla1.stdout.{:d}'
.
format
(
i
)
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla1.stderr.{:d}'
.
format
(
i
)
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'dla1.engine'
),
useDLACore
=
0
)
processes
[
'dla1'
]
.
append
(
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
))
logfiles
[
'dla1'
]
.
append
((
f_stdout
,
f_stderr
))
if
args
.
dla2
:
print
(
'Launching DLA2 process {:d}'
.
format
(
i
))
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla2.stdout.{:d}'
.
format
(
i
)
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla2.stderr.{:d}'
.
format
(
i
)
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'dla2.engine'
),
useDLACore
=
1
)
processes
[
'dla2'
]
.
append
(
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
))
logfiles
[
'dla2'
]
.
append
((
f_stdout
,
f_stderr
))
for
process_list
in
processes
.
values
():
if
process_list
==
[]:
continue
process
.
wait
()
for
p
in
process_list
:
p
.
wait
()
for
key
,
value
in
logfiles
.
items
():
if
value
==
None
:
for
key
,
file_pair_list
in
logfiles
.
items
():
if
file_pair_list
==
[]
:
continue
value
[
0
]
.
seek
(
0
,
0
)
print
(
'-'
*
40
+
'STDOUT of '
+
key
+
'-'
*
40
,
file
=
sys
.
stdout
,
end
=
'
\n
'
)
print
(
value
[
0
]
.
read
(),
file
=
sys
.
stdout
,
end
=
'
\n
'
)
print
(
'-'
*
40
+
'------end------'
+
'-'
*
40
,
file
=
sys
.
stdout
,
end
=
'
\n
'
)
value
[
1
]
.
seek
(
0
,
0
)
print
(
'-'
*
40
+
'STDERR of '
+
key
+
'-'
*
40
,
file
=
sys
.
stderr
,
end
=
'
\n
'
)
print
(
value
[
1
]
.
read
(),
file
=
sys
.
stderr
,
end
=
'
\n
'
)
print
(
'-'
*
40
+
'------end------'
+
'-'
*
40
,
file
=
sys
.
stderr
,
end
=
'
\n
'
)
for
files
in
logfiles
.
values
():
if
files
==
None
:
for
i
,
pair
in
enumerate
(
file_pair_list
):
pair
[
0
]
.
seek
(
0
,
0
)
print
(
'-'
*
40
+
'STDOUT of '
+
key
+
'-'
*
40
,
file
=
sys
.
stdout
,
end
=
'
\n
'
)
print
(
pair
[
0
]
.
read
(),
file
=
sys
.
stdout
,
end
=
'
\n
'
)
print
(
'-'
*
40
+
'------end------'
+
'-'
*
40
,
file
=
sys
.
stdout
,
end
=
'
\n
'
)
pair
[
1
]
.
seek
(
0
,
0
)
print
(
'-'
*
40
+
'STDERR of '
+
key
+
'-'
*
40
,
file
=
sys
.
stderr
,
end
=
'
\n
'
)
print
(
pair
[
1
]
.
read
(),
file
=
sys
.
stderr
,
end
=
'
\n
'
)
print
(
'-'
*
40
+
'------end------'
+
'-'
*
40
,
file
=
sys
.
stderr
,
end
=
'
\n
'
)
for
key
,
file_pair_list
in
logfiles
.
items
():
if
file_pair_list
==
[]:
continue
files
[
0
]
.
close
()
files
[
1
]
.
close
()
os
.
remove
(
files
[
0
]
.
name
)
os
.
remove
(
files
[
1
]
.
name
)
for
i
,
pair
in
enumerate
(
file_pair_list
):
pair
[
0
]
.
close
()
pair
[
1
]
.
close
()
os
.
remove
(
pair
[
0
]
.
name
)
os
.
remove
(
pair
[
1
]
.
name
)
run_benchmark_parallel.py
deleted
100644 → 0
View file @
66978061
import
subprocess
import
argparse
import
os
import
sys
parser
=
argparse
.
ArgumentParser
(
description
=
''
)
parser
.
add_argument
(
'--gpu'
,
dest
=
'gpu'
,
action
=
'store_true'
,
help
=
'Whether to use GPU for inference'
)
parser
.
add_argument
(
'--dla1'
,
dest
=
'dla1'
,
action
=
'store_true'
,
help
=
'Whether to use DLA core 1 for inference'
)
parser
.
add_argument
(
'--dla2'
,
dest
=
'dla2'
,
action
=
'store_true'
,
help
=
'Whether to use DLA core 2 for inference'
)
parser
.
add_argument
(
'--bs'
,
dest
=
'bs'
,
type
=
int
,
default
=
1
,
help
=
'Batch size of inference'
)
parser
.
add_argument
(
'--parallelruns'
,
dest
=
'parallelruns'
,
type
=
int
,
default
=
1
,
help
=
'Processes launched in parallel for each device'
)
args
=
parser
.
parse_args
()
def
gen_command
(
onnx_path
,
engine_path
,
useDLACore
):
onnx_path_arg
=
"--onnx="
+
onnx_path
engine_path_arg
=
"--loadEngine="
+
engine_path
useDLACore_arg
=
None
if
useDLACore
==
None
else
(
"--useDLACore="
+
str
(
useDLACore
))
run_command
=
[
"/usr/src/tensorrt/bin/trtexec"
]
run_command
+=
[
onnx_path_arg
]
run_command
+=
\
[
"--explicitBatch"
,
"--int8"
,
"--allowGPUFallback"
]
if
useDLACore_arg
:
run_command
+=
[
useDLACore_arg
]
run_command
+=
\
[
"--workspace=2048"
,
"--iterations=1000"
,
"--avgRuns=100"
,
"--duration=180"
,]
run_command
+=
[
engine_path_arg
]
return
run_command
processes
=
{
'gpu'
:[],
'dla1'
:[],
'dla2'
:[]
}
logfiles
=
{
'gpu'
:[],
'dla1'
:[],
'dla2'
:[]
}
for
i
in
range
(
args
.
parallelruns
):
if
args
.
gpu
:
print
(
'Launching GPU process {:d}'
.
format
(
i
))
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_gpu.stdout.{:d}'
.
format
(
i
)
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_gpu.stderr.{:d}'
.
format
(
i
)
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'gpu.engine'
),
useDLACore
=
None
)
processes
[
'gpu'
]
.
append
(
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
))
logfiles
[
'gpu'
]
.
append
((
f_stdout
,
f_stderr
))
if
args
.
dla1
:
print
(
'Launching DLA1 process {:d}'
.
format
(
i
))
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla1.stdout.{:d}'
.
format
(
i
)
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla1.stderr.{:d}'
.
format
(
i
)
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'dla1.engine'
),
useDLACore
=
0
)
processes
[
'dla1'
]
.
append
(
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
))
logfiles
[
'dla1'
]
.
append
((
f_stdout
,
f_stderr
))
if
args
.
dla2
:
print
(
'Launching DLA2 process {:d}'
.
format
(
i
))
fname_stdout
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla2.stdout.{:d}'
.
format
(
i
)
fname_stderr
=
'gpu_'
+
str
(
args
.
gpu
)
+
\
'_dla1_'
+
str
(
args
.
dla1
)
+
\
'_dla2_'
+
str
(
args
.
dla2
)
+
\
'_bs'
+
str
(
args
.
bs
)
+
\
'_dla2.stderr.{:d}'
.
format
(
i
)
f_stdout
=
open
(
fname_stdout
,
'w+'
)
f_stderr
=
open
(
fname_stderr
,
'w+'
)
bs_dir
=
'bs'
+
str
(
args
.
bs
)
command
=
gen_command
(
onnx_path
=
os
.
path
.
join
(
bs_dir
,
'model.onnx'
),
engine_path
=
os
.
path
.
join
(
bs_dir
,
'dla2.engine'
),
useDLACore
=
1
)
processes
[
'dla2'
]
.
append
(
subprocess
.
Popen
(
command
,
shell
=
False
,
stdout
=
f_stdout
,
stderr
=
f_stderr
))
logfiles
[
'dla2'
]
.
append
((
f_stdout
,
f_stderr
))
for
process_list
in
processes
.
values
():
if
process_list
==
[]:
continue
for
p
in
process_list
:
p
.
wait
()
for
key
,
file_pair_list
in
logfiles
.
items
():
if
file_pair_list
==
[]:
continue
for
i
,
pair
in
enumerate
(
file_pair_list
):
pair
[
0
]
.
seek
(
0
,
0
)
print
(
'-'
*
40
+
'STDOUT of '
+
key
+
'-'
*
40
,
file
=
sys
.
stdout
,
end
=
'
\n
'
)
print
(
pair
[
0
]
.
read
(),
file
=
sys
.
stdout
,
end
=
'
\n
'
)
print
(
'-'
*
40
+
'------end------'
+
'-'
*
40
,
file
=
sys
.
stdout
,
end
=
'
\n
'
)
pair
[
1
]
.
seek
(
0
,
0
)
print
(
'-'
*
40
+
'STDERR of '
+
key
+
'-'
*
40
,
file
=
sys
.
stderr
,
end
=
'
\n
'
)
print
(
pair
[
1
]
.
read
(),
file
=
sys
.
stderr
,
end
=
'
\n
'
)
print
(
'-'
*
40
+
'------end------'
+
'-'
*
40
,
file
=
sys
.
stderr
,
end
=
'
\n
'
)
for
key
,
file_pair_list
in
logfiles
.
items
():
if
file_pair_list
==
[]:
continue
for
i
,
pair
in
enumerate
(
file_pair_list
):
pair
[
0
]
.
close
()
pair
[
1
]
.
close
()
os
.
remove
(
pair
[
0
]
.
name
)
os
.
remove
(
pair
[
1
]
.
name
)
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment