Upload Date | September 16 2024 11:27 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-M336BU |
Model ID | samsung SM-M336BU |
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% |
226
42.0 IPS |
|
Image Classification (HP)
|
100% |
220
40.9 IPS |
|
Image Classification (Q)
|
100% |
676
125.8 IPS |
|
Image Segmentation (SP)
|
100% |
285
4.61 IPS |
|
Image Segmentation (HP)
|
100% |
287
4.66 IPS |
|
Image Segmentation (Q)
|
98% |
774
12.6 IPS |
|
Pose Estimation (SP)
|
100% |
1095
1.28 IPS |
|
Pose Estimation (HP)
|
100% |
1021
1.19 IPS |
|
Pose Estimation (Q)
|
84% |
1660
1.97 IPS |
|
Object Detection (SP)
|
100% |
217
17.2 IPS |
|
Object Detection (HP)
|
100% |
219
17.4 IPS |
|
Object Detection (Q)
|
83% |
661
53.4 IPS |
|
Face Detection (SP)
|
100% |
668
7.94 IPS |
|
Face Detection (HP)
|
100% |
669
7.94 IPS |
|
Face Detection (Q)
|
95% |
1601
19.1 IPS |
|
Depth Estimation (SP)
|
100% |
920
7.09 IPS |
|
Depth Estimation (HP)
|
99% |
800
6.16 IPS |
|
Depth Estimation (Q)
|
64% |
1559
14.3 IPS |
|
Style Transfer (SP)
|
89% |
1848
2.40 IPS |
|
Style Transfer (HP)
|
89% |
1844
2.39 IPS |
|
Style Transfer (Q)
|
98% |
3926
5.06 IPS |
|
Image Super-Resolution (SP)
|
100% |
427
15.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
430
15.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
949
35.2 IPS |
|
Text Classification (SP)
|
100% |
276
368.0 IPS |
|
Text Classification (HP)
|
100% |
281
374.8 IPS |
|
Text Classification (Q)
|
88% |
592
798.0 IPS |
|
Machine Translation (SP)
|
100% |
445
7.66 IPS |
|
Machine Translation (HP)
|
100% |
440
7.57 IPS |
|
Machine Translation (Q)
|
50% |
334
11.9 IPS |