User | mutomboken |
Upload Date | September 18 2024 08:50 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S23 Ultra |
Model ID | samsung SM-S918B |
Motherboard | kalama |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 3 Cores @ 2.02 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Cluster 3 | 1 Core @ 3.36 GHz |
Memory Information | |
---|---|
Size | 10.77 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
156
29.0 IPS |
|
Image Classification (HP)
|
100% |
164
30.5 IPS |
|
Image Classification (Q)
|
99% |
377
70.4 IPS |
|
Image Segmentation (SP)
|
100% |
224
3.64 IPS |
|
Image Segmentation (HP)
|
100% |
222
3.60 IPS |
|
Image Segmentation (Q)
|
98% |
423
6.89 IPS |
|
Pose Estimation (SP)
|
100% |
413
0.48 IPS |
|
Pose Estimation (HP)
|
100% |
440
0.51 IPS |
|
Pose Estimation (Q)
|
98% |
1751
2.05 IPS |
|
Object Detection (SP)
|
100% |
253
20.0 IPS |
|
Object Detection (HP)
|
100% |
254
20.2 IPS |
|
Object Detection (Q)
|
87% |
723
58.0 IPS |
|
Face Detection (SP)
|
100% |
611
7.26 IPS |
|
Face Detection (HP)
|
100% |
616
7.31 IPS |
|
Face Detection (Q)
|
97% |
1395
16.6 IPS |
|
Depth Estimation (SP)
|
100% |
540
4.16 IPS |
|
Depth Estimation (HP)
|
99% |
546
4.21 IPS |
|
Depth Estimation (Q)
|
64% |
1313
11.9 IPS |
|
Style Transfer (SP)
|
100% |
889
1.14 IPS |
|
Style Transfer (HP)
|
100% |
895
1.15 IPS |
|
Style Transfer (Q)
|
98% |
2216
2.86 IPS |
|
Image Super-Resolution (SP)
|
100% |
283
10.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
287
10.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1042
38.6 IPS |
|
Text Classification (SP)
|
100% |
398
531.2 IPS |
|
Text Classification (HP)
|
100% |
411
548.2 IPS |
|
Text Classification (Q)
|
91% |
643
864.1 IPS |
|
Machine Translation (SP)
|
100% |
599
10.3 IPS |
|
Machine Translation (HP)
|
100% |
593
10.2 IPS |
|
Machine Translation (Q)
|
57% |
475
11.6 IPS |