Upload Date | December 25 2024 04:24 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
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% |
273
50.8 IPS |
|
Image Classification (HP)
|
100% |
231
42.9 IPS |
|
Image Classification (Q)
|
100% |
459
85.3 IPS |
|
Image Segmentation (SP)
|
100% |
276
4.47 IPS |
|
Image Segmentation (HP)
|
100% |
268
4.34 IPS |
|
Image Segmentation (Q)
|
98% |
544
8.85 IPS |
|
Pose Estimation (SP)
|
100% |
1031
1.20 IPS |
|
Pose Estimation (HP)
|
100% |
1008
1.18 IPS |
|
Pose Estimation (Q)
|
84% |
897
1.06 IPS |
|
Object Detection (SP)
|
100% |
195
15.5 IPS |
|
Object Detection (HP)
|
100% |
185
14.6 IPS |
|
Object Detection (Q)
|
83% |
433
35.0 IPS |
|
Face Detection (SP)
|
100% |
636
7.55 IPS |
|
Face Detection (HP)
|
100% |
653
7.76 IPS |
|
Face Detection (Q)
|
95% |
1205
14.4 IPS |
|
Depth Estimation (SP)
|
100% |
801
6.17 IPS |
|
Depth Estimation (HP)
|
99% |
836
6.44 IPS |
|
Depth Estimation (Q)
|
64% |
965
8.83 IPS |
|
Style Transfer (SP)
|
89% |
1626
2.11 IPS |
|
Style Transfer (HP)
|
89% |
1622
2.11 IPS |
|
Style Transfer (Q)
|
98% |
2314
2.98 IPS |
|
Image Super-Resolution (SP)
|
100% |
474
17.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
473
17.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
637
23.6 IPS |
|
Text Classification (SP)
|
100% |
238
317.5 IPS |
|
Text Classification (HP)
|
100% |
230
307.5 IPS |
|
Text Classification (Q)
|
88% |
360
485.8 IPS |
|
Machine Translation (SP)
|
100% |
346
5.96 IPS |
|
Machine Translation (HP)
|
100% |
337
5.80 IPS |
|
Machine Translation (Q)
|
50% |
200
7.11 IPS |