Upload Date | February 06 2025 02:31 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-N975F |
Model ID | samsung SM-N975F |
Motherboard | exynos9825 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 3 revision 0 |
Base Frequency | 1.95 GHz |
Cluster 1 | 4 Cores @ 1.95 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 11.15 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
85
15.8 IPS |
|
Image Classification (HP)
|
100% |
86
16.1 IPS |
|
Image Classification (Q)
|
99% |
99
18.6 IPS |
|
Image Segmentation (SP)
|
100% |
179
2.91 IPS |
|
Image Segmentation (HP)
|
100% |
224
3.62 IPS |
|
Image Segmentation (Q)
|
98% |
90
1.46 IPS |
|
Pose Estimation (SP)
|
100% |
586
0.68 IPS |
|
Pose Estimation (HP)
|
100% |
2549
2.97 IPS |
|
Pose Estimation (Q)
|
98% |
504
0.59 IPS |
|
Object Detection (SP)
|
100% |
85
6.76 IPS |
|
Object Detection (HP)
|
100% |
86
6.79 IPS |
|
Object Detection (Q)
|
87% |
203
16.3 IPS |
|
Face Detection (SP)
|
100% |
215
2.55 IPS |
|
Face Detection (HP)
|
100% |
219
2.60 IPS |
|
Face Detection (Q)
|
97% |
196
2.33 IPS |
|
Depth Estimation (SP)
|
100% |
189
1.45 IPS |
|
Depth Estimation (HP)
|
99% |
190
1.47 IPS |
|
Depth Estimation (Q)
|
64% |
391
3.55 IPS |
|
Style Transfer (SP)
|
100% |
252
0.32 IPS |
|
Style Transfer (HP)
|
100% |
338
0.43 IPS |
|
Style Transfer (Q)
|
98% |
187
0.24 IPS |
|
Image Super-Resolution (SP)
|
100% |
312
11.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
664
24.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
100
3.70 IPS |
|
Text Classification (SP)
|
100% |
38
50.6 IPS |
|
Text Classification (HP)
|
100% |
115
153.9 IPS |
|
Text Classification (Q)
|
91% |
33
44.4 IPS |
|
Machine Translation (SP)
|
100% |
218
3.76 IPS |
|
Machine Translation (HP)
|
100% |
271
4.67 IPS |
|
Machine Translation (Q)
|
57% |
281
6.86 IPS |