Upload Date | April 08 2025 09:16 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S9360 |
Model ID | samsung SM-S9360 |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.47 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2136
397.3 IPS |
|
Image Classification (HP)
|
100% |
2087
388.1 IPS |
|
Image Classification (Q)
|
100% |
4577
851.2 IPS |
|
Image Segmentation (SP)
|
100% |
2547
41.3 IPS |
|
Image Segmentation (HP)
|
100% |
2481
40.2 IPS |
|
Image Segmentation (Q)
|
98% |
5536
90.0 IPS |
|
Pose Estimation (SP)
|
100% |
5509
6.43 IPS |
|
Pose Estimation (HP)
|
100% |
4253
4.96 IPS |
|
Pose Estimation (Q)
|
84% |
9807
11.6 IPS |
|
Object Detection (SP)
|
98% |
1435
114.2 IPS |
|
Object Detection (HP)
|
98% |
1420
113.0 IPS |
|
Object Detection (Q)
|
83% |
2539
205.1 IPS |
|
Face Detection (SP)
|
100% |
3969
47.2 IPS |
|
Face Detection (HP)
|
100% |
4438
52.7 IPS |
|
Face Detection (Q)
|
95% |
8897
106.2 IPS |
|
Depth Estimation (SP)
|
99% |
4567
35.3 IPS |
|
Depth Estimation (HP)
|
99% |
4808
37.1 IPS |
|
Depth Estimation (Q)
|
64% |
10516
96.3 IPS |
|
Style Transfer (SP)
|
89% |
10306
13.4 IPS |
|
Style Transfer (HP)
|
89% |
9785
12.7 IPS |
|
Style Transfer (Q)
|
98% |
19555
25.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
1726
63.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
1900
70.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
4813
178.3 IPS |
|
Text Classification (SP)
|
100% |
858
1.14 KIPS |
|
Text Classification (HP)
|
99% |
956
1.28 KIPS |
|
Text Classification (Q)
|
88% |
1037
1.40 KIPS |
|
Machine Translation (SP)
|
100% |
1436
24.7 IPS |
|
Machine Translation (HP)
|
100% |
1316
22.7 IPS |
|
Machine Translation (Q)
|
50% |
390
13.9 IPS |