ABCDEFGHI
1
Results for BODY_25 model (OpenPose >= v1.5.0), COCO model (default until OpenPose 1.4.0) is about 35% slower on GPU but 3x faster on CPU
2
OpenPose 1.5.0 benchmark
Leave a comment on this document if you try on a different graphics card and have its running time!
3
Server graphics card model#GPUs
Millisec / frame body-only+
FPS body-only+
GPU memory body (MiB)*+
Fps all (body,hands,face)+
GPU memory all (MiB)*+
Flags3rd party and OS for that measurement
4
Nvidia V100cuDNN 7, CUDA 9, OpenCV 3.0
5
Nvidia p100cuDNN 5.1, CUDA 8
6
Nvidia k80
7
8
Graphics card model#GPUs
Millisec / frame body-only+
FPS body-only+
GPU memory body (MiB)*+
Fps all (body,hands,face)+
GPU memory all (MiB)*+
Flags3rd party and OS for that measurement
9
GTX 1080 Ti (11GB)**146.121.72413~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe custom
10
Titan X Pascal (12GB)156.817.62221~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0
11
GTX 1080 (8GB)1~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0
12
GTX 1070 (8GB)**1~1/2 or 1/3 of body-only~2 x body memory
--resolution "640x480" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0, Windows
13
Quadro M6000 (24GB)**1~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0, Windows
14
GTX 980 (8GB)**1~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0
15
GTX 1060 Ti (3GB)**1~8.9~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 6, CUDA 8, Caffe 1.0.0, Windows
16
GTX 780 Ti**1~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0, Windows
17
GTX 1050 Ti (4GB)1~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0
18
GTX 960 (4GB)**1~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 6.0, CUDA 8, Caffe 1.0.0
19
GTX 965 (2GB)**1Out of memoryOut of memoryOut of memoryOut of memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0
20
GTX 750 Ti**1Out of memoryOut of memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0
21
GTX 860 (2GB)1Out of memoryOut of memoryOut of memoryOut of memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0
22
GeForce 940MX (4GB)**1~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0, Windows
23
GTX 660 (2GB)**1Out of memoryOut of memoryOut of memoryOut of memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 6.0, CUDA 8, Caffe 1.0.0
24
Quadro K3000M (10GB)**1~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0, Windows
25
GeForce GT 740 (2GB)**1Out of memoryOut of memoryOut of memoryOut of memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 6.0, CUDA 8, Caffe 1.0.0
26
AMD Radeon RX 560 (4GB)1Out of memoryOut of memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
ROCM 1.8, Ubuntu 16.04, Windows
27
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 6.0, CUDA 8, Caffe 1.0.0
28
Graphic cards combination#GPUs
Millisec / frame body-only+
FPS body-only+
GPU memory body (MiB)*+
Fps all (body,hands,face)+
GPU memory all (MiB)*+
Flags3rd party and OS for that measurement
29
GTX 1080 Ti + Titan X Pascal226.038.4~1/2 or 1/3 of body-only~2 x body memory
--resolution "1280x720" --net_resolution "656x368" --num_scales 1
cuDNN 5.1, CUDA 8, Caffe 1.0.0
30
31
Intel CPU version (no GPU) (alpha version)
#Cores
Millisec / frame body-only+
FPS body-only+RAM memory (MB)
Fps all (body,hands,face)+
GPU memory all (MiB)*+
Flags3rd party and OS for that measurement
32
i9-7900X (MKL - 8 OMP - 8)20~0.440000--net_resolution "-1x368" --model_pose COCOcuDNN 5.1, CUDA 8, Intel Caffe (MKL)
33
i9-7900X (MKL - 1 OMP - 1)20~0.26020--net_resolution "-1x368" --model_pose COCOcuDNN 5.1, CUDA 8, Intel Caffe (MKL)
34
Intel Core i7-6850K122293.00.49244--net_resolution "-1x368" --model_pose COCO
cuDNN 5.1, CUDA 8, Intel Caffe (MKL), OpenCV 3.3
35
i7-6700K (MKL - 4 OMP - 4)8~0.37231--net_resolution "-1x368" --model_pose COCOcuDNN 5.1, CUDA 8, Intel Caffe (MKL)
36
i7-6700K (MKL - 1 OMP - 1)8~0.12521--net_resolution "-1x368" --model_pose COCOcuDNN 5.1, CUDA 8, Intel Caffe (MKL)
37
i7-4710HQ85190.00.26723--net_resolution "-1x368" --model_pose COCO
cuDNN 5.1, CUDA 8, Intel Caffe (MKL), OpenCV 3.3
38
i7-4710HQ87173.00.18030--net_resolution "-1x368" --model_pose COCOcuDNN 5.1, CUDA 8, Caffe 1.0.0, Windows
39
40
Intel CPU (-accuracy to increase speed)
#Cores
Millisec / frame body-only+
FPS body-only***RAM memory (MB)
Fps all (body,hands,face)+
GPU memory all (MiB)*+
Flags3rd party and OS for that measurement
41
i9-7900X (MKL - 8 OMP - 8)20~1.75820
--net_resolution "-1x256" --model_pose COCO (lower accuracy)
cuDNN 5.1, CUDA 8, Intel Caffe (MKL)
42
i9-7900X (MKL - 1 OMP - 1)20~0.71620
--net_resolution "-1x256" --model_pose COCO (lower accuracy)
cuDNN 5.1, CUDA 8, Intel Caffe (MKL)
43
i7-6700K (MKL - 4 OMP - 4)8~0.94100
--net_resolution "-1x256" --model_pose COCO (lower accuracy)
cuDNN 5.1, CUDA 8, Intel Caffe (MKL)
44
i7-6700K (MKL - 1 OMP - 1)8~0.32381
--net_resolution "-1x256" --model_pose COCO (lower accuracy)
cuDNN 5.1, CUDA 8, Intel Caffe (MKL)
45
i7-4710HQ83553.00.35322
--net_resolution "-1x256" --model_pose COCO (lower accuracy)
cuDNN 5.1, CUDA 8, Intel Caffe (MKL), OpenCV 3.3
46
i7-4710HQ82149.00.53650
--net_resolution "-1x256" --model_pose COCO (lower accuracy)
cuDNN 5.1, CUDA 8, Intel Caffe (MKL), OpenCV 3.3
47
48
Ubuntu (non Intel) and Mac OS
49
i7-4710HQ0.120000--net_resolution "-1x368" --model_pose COCOcuDNN 5.1, CUDA 8, Caffe
50
51
52
53
* According to the bash command: `nvidia-smi`
54
+ Values dependent of 3rdparty libraries (OpenCV, Caffe, ...)
55
** Values added based on user comments
56
*** Lower accuracy in order to speed up the code
57
58
Other Notes
59
cuDNN 6.0 is ~15% slower than 5.1 in our tests
60
The ~ symbol means approx
61
62
63
64
65
66
67
68
69