Upload Date | September 18 2024 08:43 AM |
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-A5360 |
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 | 7.22 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
197
36.7 IPS |
|
Image Classification (HP)
|
100% |
179
33.2 IPS |
|
Image Classification (Q)
|
100% |
495
92.0 IPS |
|
Image Segmentation (SP)
|
100% |
214
3.47 IPS |
|
Image Segmentation (HP)
|
100% |
215
3.49 IPS |
|
Image Segmentation (Q)
|
98% |
570
9.27 IPS |
|
Pose Estimation (SP)
|
100% |
842
0.98 IPS |
|
Pose Estimation (HP)
|
100% |
833
0.97 IPS |
|
Pose Estimation (Q)
|
84% |
1199
1.42 IPS |
|
Object Detection (SP)
|
100% |
164
13.0 IPS |
|
Object Detection (HP)
|
100% |
165
13.1 IPS |
|
Object Detection (Q)
|
83% |
487
39.3 IPS |
|
Face Detection (SP)
|
100% |
533
6.34 IPS |
|
Face Detection (HP)
|
100% |
531
6.31 IPS |
|
Face Detection (Q)
|
95% |
1183
14.1 IPS |
|
Depth Estimation (SP)
|
100% |
716
5.52 IPS |
|
Depth Estimation (HP)
|
99% |
708
5.45 IPS |
|
Depth Estimation (Q)
|
64% |
1137
10.4 IPS |
|
Style Transfer (SP)
|
89% |
1393
1.81 IPS |
|
Style Transfer (HP)
|
89% |
1403
1.82 IPS |
|
Style Transfer (Q)
|
98% |
2882
3.72 IPS |
|
Image Super-Resolution (SP)
|
100% |
370
13.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
369
13.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
692
25.6 IPS |
|
Text Classification (SP)
|
100% |
198
264.8 IPS |
|
Text Classification (HP)
|
100% |
196
262.1 IPS |
|
Text Classification (Q)
|
88% |
400
539.6 IPS |
|
Machine Translation (SP)
|
100% |
333
5.73 IPS |
|
Machine Translation (HP)
|
100% |
329
5.67 IPS |
|
Machine Translation (Q)
|
50% |
252
8.96 IPS |