Upload Date | November 17 2024 08:55 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
157
29.3 IPS |
|
Image Classification (HP)
|
100% |
283
52.6 IPS |
|
Image Classification (Q)
|
99% |
271
50.6 IPS |
|
Image Segmentation (SP)
|
100% |
232
3.76 IPS |
|
Image Segmentation (HP)
|
100% |
387
6.27 IPS |
|
Image Segmentation (Q)
|
98% |
391
6.37 IPS |
|
Pose Estimation (SP)
|
100% |
153
0.18 IPS |
|
Pose Estimation (HP)
|
100% |
180
0.21 IPS |
|
Pose Estimation (Q)
|
96% |
179
0.21 IPS |
|
Object Detection (SP)
|
100% |
142
11.2 IPS |
|
Object Detection (HP)
|
100% |
237
18.8 IPS |
|
Object Detection (Q)
|
83% |
230
18.6 IPS |
|
Face Detection (SP)
|
100% |
549
6.53 IPS |
|
Face Detection (HP)
|
100% |
818
9.72 IPS |
|
Face Detection (Q)
|
97% |
760
9.06 IPS |
|
Depth Estimation (SP)
|
100% |
296
2.28 IPS |
|
Depth Estimation (HP)
|
99% |
381
2.94 IPS |
|
Depth Estimation (Q)
|
62% |
309
2.92 IPS |
|
Style Transfer (SP)
|
100% |
596
0.77 IPS |
|
Style Transfer (HP)
|
100% |
841
1.08 IPS |
|
Style Transfer (Q)
|
98% |
838
1.08 IPS |
|
Image Super-Resolution (SP)
|
100% |
158
5.85 IPS |
|
Image Super-Resolution (HP)
|
100% |
244
9.02 IPS |
|
Image Super-Resolution (Q)
|
97% |
242
8.96 IPS |
|
Text Classification (SP)
|
100% |
167
223.1 IPS |
|
Text Classification (HP)
|
100% |
169
226.1 IPS |
|
Text Classification (Q)
|
91% |
333
447.3 IPS |
|
Machine Translation (SP)
|
100% |
280
4.82 IPS |
|
Machine Translation (HP)
|
100% |
279
4.80 IPS |
|
Machine Translation (Q)
|
57% |
269
6.58 IPS |