Upload Date | November 17 2024 08:25 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Samsung Exynos 1280 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy A53 5G |
Model ID | samsung SM-A536B |
Motherboard | s5e8825 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
219
40.6 IPS |
|
Image Classification (HP)
|
100% |
223
41.5 IPS |
|
Image Classification (Q)
|
100% |
715
133.0 IPS |
|
Image Segmentation (SP)
|
100% |
281
4.56 IPS |
|
Image Segmentation (HP)
|
100% |
282
4.58 IPS |
|
Image Segmentation (Q)
|
98% |
793
12.9 IPS |
|
Pose Estimation (SP)
|
100% |
1083
1.26 IPS |
|
Pose Estimation (HP)
|
100% |
997
1.16 IPS |
|
Pose Estimation (Q)
|
84% |
1304
1.55 IPS |
|
Object Detection (SP)
|
100% |
161
12.7 IPS |
|
Object Detection (HP)
|
100% |
162
12.8 IPS |
|
Object Detection (Q)
|
83% |
487
39.4 IPS |
|
Face Detection (SP)
|
100% |
500
5.94 IPS |
|
Face Detection (HP)
|
100% |
505
5.99 IPS |
|
Face Detection (Q)
|
95% |
1175
14.0 IPS |
|
Depth Estimation (SP)
|
100% |
675
5.20 IPS |
|
Depth Estimation (HP)
|
99% |
680
5.24 IPS |
|
Depth Estimation (Q)
|
64% |
1131
10.4 IPS |
|
Style Transfer (SP)
|
89% |
1387
1.80 IPS |
|
Style Transfer (HP)
|
89% |
1368
1.78 IPS |
|
Style Transfer (Q)
|
98% |
2868
3.70 IPS |
|
Image Super-Resolution (SP)
|
100% |
351
13.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
344
12.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
688
25.5 IPS |
|
Text Classification (SP)
|
100% |
198
264.6 IPS |
|
Text Classification (HP)
|
100% |
196
261.8 IPS |
|
Text Classification (Q)
|
88% |
391
527.3 IPS |
|
Machine Translation (SP)
|
100% |
327
5.63 IPS |
|
Machine Translation (HP)
|
100% |
323
5.57 IPS |
|
Machine Translation (Q)
|
50% |
246
8.72 IPS |