User | benched |
Upload Date | October 23 2024 04:47 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 13 |
Model | samsung SM-G715FN |
Model ID | samsung SM-G715FN |
Motherboard | exynos9611 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3337 revision 2 |
Base Frequency | 1.74 GHz |
Cluster 1 | 4 Cores @ 1.74 GHz |
Cluster 2 | 4 Cores @ 2.31 GHz |
Memory Information | |
---|---|
Size | 3.49 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
108
20.2 IPS |
|
Image Classification (HP)
|
100% |
180
33.4 IPS |
|
Image Classification (Q)
|
99% |
172
32.0 IPS |
|
Image Segmentation (SP)
|
100% |
117
1.90 IPS |
|
Image Segmentation (HP)
|
100% |
160
2.59 IPS |
|
Image Segmentation (Q)
|
98% |
156
2.54 IPS |
|
Pose Estimation (SP)
|
100% |
81
0.09 IPS |
|
Pose Estimation (HP)
|
100% |
109
0.13 IPS |
|
Pose Estimation (Q)
|
96% |
109
0.13 IPS |
|
Object Detection (SP)
|
100% |
86
6.84 IPS |
|
Object Detection (HP)
|
100% |
145
11.5 IPS |
|
Object Detection (Q)
|
83% |
97
7.83 IPS |
|
Face Detection (SP)
|
100% |
216
2.57 IPS |
|
Face Detection (HP)
|
100% |
303
3.59 IPS |
|
Face Detection (Q)
|
97% |
425
5.07 IPS |
|
Depth Estimation (SP)
|
100% |
177
1.37 IPS |
|
Depth Estimation (HP)
|
99% |
162
1.25 IPS |
|
Depth Estimation (Q)
|
62% |
201
1.90 IPS |
|
Style Transfer (SP)
|
100% |
333
0.43 IPS |
|
Style Transfer (HP)
|
100% |
548
0.70 IPS |
|
Style Transfer (Q)
|
98% |
545
0.70 IPS |
|
Image Super-Resolution (SP)
|
100% |
117
4.33 IPS |
|
Image Super-Resolution (HP)
|
100% |
117
4.31 IPS |
|
Image Super-Resolution (Q)
|
97% |
115
4.26 IPS |
|
Text Classification (SP)
|
100% |
47
62.6 IPS |
|
Text Classification (HP)
|
100% |
48
64.2 IPS |
|
Text Classification (Q)
|
91% |
61
82.6 IPS |
|
Machine Translation (SP)
|
100% |
84
1.45 IPS |
|
Machine Translation (HP)
|
100% |
84
1.45 IPS |
|
Machine Translation (Q)
|
57% |
63
1.54 IPS |