User | for_geekbench |
Upload Date | April 01 2025 02:37 PM |
Views | 11 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Samsung Exynos 9820 |
System Information | |
---|---|
Operating System | Android 12 |
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% |
268
49.8 IPS |
|
Image Classification (HP)
|
100% |
359
66.8 IPS |
|
Image Classification (Q)
|
99% |
337
62.9 IPS |
|
Image Segmentation (SP)
|
100% |
297
4.82 IPS |
|
Image Segmentation (HP)
|
100% |
391
6.34 IPS |
|
Image Segmentation (Q)
|
98% |
357
5.81 IPS |
|
Pose Estimation (SP)
|
100% |
187
0.22 IPS |
|
Pose Estimation (HP)
|
100% |
262
0.31 IPS |
|
Pose Estimation (Q)
|
96% |
261
0.31 IPS |
|
Object Detection (SP)
|
100% |
232
18.4 IPS |
|
Object Detection (HP)
|
100% |
318
25.2 IPS |
|
Object Detection (Q)
|
83% |
294
23.8 IPS |
|
Face Detection (SP)
|
100% |
911
10.8 IPS |
|
Face Detection (HP)
|
100% |
1217
14.5 IPS |
|
Face Detection (Q)
|
97% |
1116
13.3 IPS |
|
Depth Estimation (SP)
|
100% |
466
3.59 IPS |
|
Depth Estimation (HP)
|
99% |
642
4.94 IPS |
|
Depth Estimation (Q)
|
62% |
436
4.13 IPS |
|
Style Transfer (SP)
|
100% |
906
1.17 IPS |
|
Style Transfer (HP)
|
100% |
1448
1.86 IPS |
|
Style Transfer (Q)
|
98% |
1442
1.86 IPS |
|
Image Super-Resolution (SP)
|
100% |
261
9.63 IPS |
|
Image Super-Resolution (HP)
|
100% |
352
13.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
346
12.8 IPS |
|
Text Classification (SP)
|
100% |
240
319.7 IPS |
|
Text Classification (HP)
|
100% |
239
318.8 IPS |
|
Text Classification (Q)
|
91% |
385
517.6 IPS |
|
Machine Translation (SP)
|
100% |
411
7.07 IPS |
|
Machine Translation (HP)
|
100% |
405
6.97 IPS |
|
Machine Translation (Q)
|
57% |
324
7.93 IPS |