Upload Date | June 16 2025 09:33 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Samsung Exynos 9820 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S10 |
Model ID | samsung SM-G973F |
Motherboard | exynos9820 |
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 @ 2.31 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 7.25 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
160
29.8 IPS |
|
Image Classification (HP)
|
100% |
158
29.3 IPS |
|
Image Classification (Q)
|
99% |
314
58.6 IPS |
|
Image Segmentation (SP)
|
100% |
200
3.24 IPS |
|
Image Segmentation (HP)
|
100% |
202
3.28 IPS |
|
Image Segmentation (Q)
|
98% |
353
5.74 IPS |
|
Pose Estimation (SP)
|
100% |
252
0.29 IPS |
|
Pose Estimation (HP)
|
100% |
237
0.28 IPS |
|
Pose Estimation (Q)
|
98% |
796
0.93 IPS |
|
Object Detection (SP)
|
100% |
128
10.2 IPS |
|
Object Detection (HP)
|
100% |
128
10.2 IPS |
|
Object Detection (Q)
|
87% |
316
25.3 IPS |
|
Face Detection (SP)
|
100% |
325
3.86 IPS |
|
Face Detection (HP)
|
100% |
323
3.84 IPS |
|
Face Detection (Q)
|
97% |
684
8.16 IPS |
|
Depth Estimation (SP)
|
100% |
272
2.09 IPS |
|
Depth Estimation (HP)
|
99% |
269
2.07 IPS |
|
Depth Estimation (Q)
|
64% |
574
5.21 IPS |
|
Style Transfer (SP)
|
100% |
480
0.62 IPS |
|
Style Transfer (HP)
|
100% |
480
0.62 IPS |
|
Style Transfer (Q)
|
98% |
1168
1.51 IPS |
|
Image Super-Resolution (SP)
|
100% |
139
5.13 IPS |
|
Image Super-Resolution (HP)
|
100% |
138
5.09 IPS |
|
Image Super-Resolution (Q)
|
97% |
446
16.5 IPS |
|
Text Classification (SP)
|
100% |
197
262.7 IPS |
|
Text Classification (HP)
|
100% |
201
268.4 IPS |
|
Text Classification (Q)
|
91% |
329
441.7 IPS |
|
Machine Translation (SP)
|
100% |
290
4.99 IPS |
|
Machine Translation (HP)
|
100% |
274
4.72 IPS |
|
Machine Translation (Q)
|
57% |
217
5.31 IPS |