Upload Date | April 02 2025 07:29 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S9380 |
Model ID | samsung SM-S9380 |
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 | 14.75 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
648
120.5 IPS |
|
Image Classification (HP)
|
100% |
975
181.3 IPS |
|
Image Classification (Q)
|
99% |
1243
231.9 IPS |
|
Image Segmentation (SP)
|
100% |
1624
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
2029
32.9 IPS |
|
Image Segmentation (Q)
|
98% |
1211
19.7 IPS |
|
Pose Estimation (SP)
|
100% |
1723
2.01 IPS |
|
Pose Estimation (HP)
|
100% |
2976
3.47 IPS |
|
Pose Estimation (Q)
|
96% |
2805
3.29 IPS |
|
Object Detection (SP)
|
100% |
510
40.5 IPS |
|
Object Detection (HP)
|
100% |
1090
86.4 IPS |
|
Object Detection (Q)
|
86% |
1057
84.9 IPS |
|
Face Detection (SP)
|
100% |
2881
34.2 IPS |
|
Face Detection (HP)
|
100% |
5606
66.6 IPS |
|
Face Detection (Q)
|
97% |
3174
37.9 IPS |
|
Depth Estimation (SP)
|
100% |
1681
12.9 IPS |
|
Depth Estimation (HP)
|
99% |
4958
38.3 IPS |
|
Depth Estimation (Q)
|
63% |
3965
36.9 IPS |
|
Style Transfer (SP)
|
100% |
5620
7.22 IPS |
|
Style Transfer (HP)
|
100% |
11985
15.4 IPS |
|
Style Transfer (Q)
|
98% |
12277
15.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
641
23.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
2058
76.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
1941
71.9 IPS |
|
Text Classification (SP)
|
100% |
672
897.1 IPS |
|
Text Classification (HP)
|
100% |
689
919.3 IPS |
|
Text Classification (Q)
|
91% |
1073
1.44 KIPS |
|
Machine Translation (SP)
|
100% |
1041
17.9 IPS |
|
Machine Translation (HP)
|
100% |
1026
17.7 IPS |
|
Machine Translation (Q)
|
57% |
747
18.2 IPS |