User | benched |
Upload Date | October 24 2024 09:35 AM |
Views | 12 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
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% |
136
25.4 IPS |
|
Image Classification (HP)
|
100% |
134
24.9 IPS |
|
Image Classification (Q)
|
100% |
221
41.0 IPS |
|
Image Segmentation (SP)
|
100% |
168
2.72 IPS |
|
Image Segmentation (HP)
|
100% |
168
2.72 IPS |
|
Image Segmentation (Q)
|
98% |
300
4.88 IPS |
|
Pose Estimation (SP)
|
100% |
602
0.70 IPS |
|
Pose Estimation (HP)
|
100% |
596
0.69 IPS |
|
Pose Estimation (Q)
|
84% |
457
0.54 IPS |
|
Object Detection (SP)
|
100% |
115
9.13 IPS |
|
Object Detection (HP)
|
100% |
114
9.06 IPS |
|
Object Detection (Q)
|
83% |
212
17.1 IPS |
|
Face Detection (SP)
|
100% |
352
4.19 IPS |
|
Face Detection (HP)
|
100% |
351
4.17 IPS |
|
Face Detection (Q)
|
95% |
515
6.15 IPS |
|
Depth Estimation (SP)
|
100% |
468
3.60 IPS |
|
Depth Estimation (HP)
|
99% |
449
3.46 IPS |
|
Depth Estimation (Q)
|
64% |
488
4.47 IPS |
|
Style Transfer (SP)
|
89% |
994
1.29 IPS |
|
Style Transfer (HP)
|
89% |
972
1.26 IPS |
|
Style Transfer (Q)
|
98% |
1298
1.67 IPS |
|
Image Super-Resolution (SP)
|
100% |
257
9.50 IPS |
|
Image Super-Resolution (HP)
|
100% |
251
9.26 IPS |
|
Image Super-Resolution (Q)
|
97% |
278
10.3 IPS |
|
Text Classification (SP)
|
100% |
129
171.7 IPS |
|
Text Classification (HP)
|
100% |
128
170.6 IPS |
|
Text Classification (Q)
|
88% |
184
247.8 IPS |
|
Machine Translation (SP)
|
100% |
214
3.69 IPS |
|
Machine Translation (HP)
|
100% |
208
3.59 IPS |
|
Machine Translation (Q)
|
50% |
120
4.25 IPS |