Upload Date | May 17 2025 04:05 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM SM8350 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-G990B2 |
Model ID | samsung SM-G990B2 |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM SM8350 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.19 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
419
77.8 IPS |
|
Image Classification (HP)
|
100% |
450
83.8 IPS |
|
Image Classification (Q)
|
100% |
1284
238.8 IPS |
|
Image Segmentation (SP)
|
100% |
500
8.11 IPS |
|
Image Segmentation (HP)
|
100% |
517
8.38 IPS |
|
Image Segmentation (Q)
|
98% |
1493
24.3 IPS |
|
Pose Estimation (SP)
|
100% |
1741
2.03 IPS |
|
Pose Estimation (HP)
|
100% |
1788
2.09 IPS |
|
Pose Estimation (Q)
|
84% |
2469
2.93 IPS |
|
Object Detection (SP)
|
100% |
349
27.7 IPS |
|
Object Detection (HP)
|
100% |
364
28.9 IPS |
|
Object Detection (Q)
|
83% |
981
79.2 IPS |
|
Face Detection (SP)
|
100% |
934
11.1 IPS |
|
Face Detection (HP)
|
100% |
986
11.7 IPS |
|
Face Detection (Q)
|
95% |
2351
28.1 IPS |
|
Depth Estimation (SP)
|
100% |
1315
10.1 IPS |
|
Depth Estimation (HP)
|
99% |
1348
10.4 IPS |
|
Depth Estimation (Q)
|
64% |
2117
19.4 IPS |
|
Style Transfer (SP)
|
89% |
2619
3.40 IPS |
|
Style Transfer (HP)
|
89% |
2711
3.52 IPS |
|
Style Transfer (Q)
|
98% |
5356
6.91 IPS |
|
Image Super-Resolution (SP)
|
100% |
296
10.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
294
10.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
628
23.3 IPS |
|
Text Classification (SP)
|
100% |
165
219.7 IPS |
|
Text Classification (HP)
|
100% |
165
219.9 IPS |
|
Text Classification (Q)
|
88% |
268
361.3 IPS |
|
Machine Translation (SP)
|
100% |
250
4.31 IPS |
|
Machine Translation (HP)
|
100% |
242
4.17 IPS |
|
Machine Translation (Q)
|
50% |
155
5.50 IPS |