Upload Date | November 24 2024 08:51 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Samsung Exynos 1380 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy A54 |
Model ID | samsung SM-A546B |
Motherboard | s5e8835 |
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 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
93
17.4 IPS |
|
Image Classification (HP)
|
100% |
103
19.1 IPS |
|
Image Classification (Q)
|
99% |
298
55.5 IPS |
|
Image Segmentation (SP)
|
100% |
310
5.02 IPS |
|
Image Segmentation (HP)
|
100% |
446
7.23 IPS |
|
Image Segmentation (Q)
|
98% |
379
6.16 IPS |
|
Pose Estimation (SP)
|
0% |
0
0.10 IPS |
|
Pose Estimation (HP)
|
0% |
0
2.89 IPS |
|
Pose Estimation (Q)
|
98% |
880
1.03 IPS |
|
Object Detection (SP)
|
100% |
126
10.0 IPS |
|
Object Detection (HP)
|
100% |
127
10.0 IPS |
|
Object Detection (Q)
|
87% |
367
29.4 IPS |
|
Face Detection (SP)
|
100% |
327
3.89 IPS |
|
Face Detection (HP)
|
100% |
329
3.91 IPS |
|
Face Detection (Q)
|
97% |
737
8.79 IPS |
|
Depth Estimation (SP)
|
100% |
277
2.13 IPS |
|
Depth Estimation (HP)
|
99% |
279
2.15 IPS |
|
Depth Estimation (Q)
|
64% |
682
6.19 IPS |
|
Style Transfer (SP)
|
100% |
483
0.62 IPS |
|
Style Transfer (HP)
|
100% |
483
0.62 IPS |
|
Style Transfer (Q)
|
98% |
1346
1.74 IPS |
|
Image Super-Resolution (SP)
|
100% |
71
2.64 IPS |
|
Image Super-Resolution (HP)
|
100% |
859
31.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
484
17.9 IPS |
|
Text Classification (SP)
|
100% |
181
241.3 IPS |
|
Text Classification (HP)
|
100% |
181
241.5 IPS |
|
Text Classification (Q)
|
91% |
346
464.9 IPS |
|
Machine Translation (SP)
|
100% |
306
5.27 IPS |
|
Machine Translation (HP)
|
100% |
307
5.28 IPS |
|
Machine Translation (Q)
|
57% |
288
7.03 IPS |