Upload Date | June 01 2025 08:05 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S936B |
Model ID | samsung SM-S936B |
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% |
721
134.2 IPS |
|
Image Classification (HP)
|
100% |
1805
335.7 IPS |
|
Image Classification (Q)
|
99% |
1484
276.7 IPS |
|
Image Segmentation (SP)
|
100% |
1473
23.9 IPS |
|
Image Segmentation (HP)
|
100% |
2115
34.3 IPS |
|
Image Segmentation (Q)
|
98% |
2146
34.9 IPS |
|
Pose Estimation (SP)
|
100% |
1712
2.00 IPS |
|
Pose Estimation (HP)
|
100% |
2975
3.47 IPS |
|
Pose Estimation (Q)
|
96% |
2985
3.50 IPS |
|
Object Detection (SP)
|
100% |
575
45.6 IPS |
|
Object Detection (HP)
|
100% |
1172
92.9 IPS |
|
Object Detection (Q)
|
86% |
1068
85.8 IPS |
|
Face Detection (SP)
|
100% |
3400
40.4 IPS |
|
Face Detection (HP)
|
100% |
4229
50.2 IPS |
|
Face Detection (Q)
|
97% |
4165
49.7 IPS |
|
Depth Estimation (SP)
|
100% |
1694
13.0 IPS |
|
Depth Estimation (HP)
|
99% |
4927
38.1 IPS |
|
Depth Estimation (Q)
|
63% |
4077
37.9 IPS |
|
Style Transfer (SP)
|
100% |
6288
8.08 IPS |
|
Style Transfer (HP)
|
100% |
13496
17.3 IPS |
|
Style Transfer (Q)
|
98% |
13414
17.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
681
25.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
2381
87.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
2251
83.4 IPS |
|
Text Classification (SP)
|
100% |
677
903.0 IPS |
|
Text Classification (HP)
|
100% |
672
897.0 IPS |
|
Text Classification (Q)
|
91% |
1083
1.46 KIPS |
|
Machine Translation (SP)
|
100% |
1042
17.9 IPS |
|
Machine Translation (HP)
|
100% |
1030
17.7 IPS |
|
Machine Translation (Q)
|
57% |
679
16.6 IPS |