User | paultissue |
Upload Date | September 03 2025 11:53 PM |
Views | 10 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A526U |
Model ID | samsung SM-A526U |
Motherboard | lito |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 5.30 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
263
49.0 IPS |
|
Image Classification (HP)
|
100% |
442
82.3 IPS |
|
Image Classification (Q)
|
99% |
415
77.4 IPS |
|
Image Segmentation (SP)
|
100% |
399
6.46 IPS |
|
Image Segmentation (HP)
|
100% |
645
10.5 IPS |
|
Image Segmentation (Q)
|
98% |
605
9.84 IPS |
|
Pose Estimation (SP)
|
100% |
1436
1.68 IPS |
|
Pose Estimation (HP)
|
99% |
2373
2.77 IPS |
|
Pose Estimation (Q)
|
97% |
2333
2.73 IPS |
|
Object Detection (SP)
|
100% |
228
18.1 IPS |
|
Object Detection (HP)
|
99% |
376
29.8 IPS |
|
Object Detection (Q)
|
85% |
355
28.5 IPS |
|
Face Detection (SP)
|
100% |
793
9.42 IPS |
|
Face Detection (HP)
|
100% |
1340
15.9 IPS |
|
Face Detection (Q)
|
97% |
1165
13.9 IPS |
|
Depth Estimation (SP)
|
100% |
871
6.71 IPS |
|
Depth Estimation (HP)
|
98% |
1461
11.3 IPS |
|
Depth Estimation (Q)
|
65% |
1213
10.9 IPS |
|
Style Transfer (SP)
|
100% |
1884
2.42 IPS |
|
Style Transfer (HP)
|
100% |
3618
4.65 IPS |
|
Style Transfer (Q)
|
98% |
3498
4.51 IPS |
|
Image Super-Resolution (SP)
|
100% |
372
13.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
628
23.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
617
22.9 IPS |
|
Text Classification (SP)
|
35% |
16
152.4 IPS |
|
Text Classification (HP)
|
35% |
24
220.2 IPS |
|
Text Classification (Q)
|
35% |
24
217.4 IPS |
|
Machine Translation (SP)
|
100% |
224
3.85 IPS |
|
Machine Translation (HP)
|
97% |
297
5.13 IPS |
|
Machine Translation (Q)
|
64% |
230
4.73 IPS |