User | Kekko01 |
Upload Date | August 17 2024 10:06 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X510 |
Model ID | samsung SM-X510 |
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 | 5.57 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
123
22.9 IPS |
|
Image Classification (HP)
|
100% |
124
23.0 IPS |
|
Image Classification (Q)
|
97% |
332
61.9 IPS |
|
Image Segmentation (SP)
|
100% |
302
4.90 IPS |
|
Image Segmentation (HP)
|
100% |
440
7.14 IPS |
|
Image Segmentation (Q)
|
98% |
376
6.11 IPS |
|
Pose Estimation (SP)
|
100% |
90
0.10 IPS |
|
Pose Estimation (HP)
|
99% |
2462
2.87 IPS |
|
Pose Estimation (Q)
|
98% |
855
1.00 IPS |
|
Object Detection (SP)
|
100% |
124
9.83 IPS |
|
Object Detection (HP)
|
100% |
125
9.88 IPS |
|
Object Detection (Q)
|
89% |
361
28.9 IPS |
|
Face Detection (SP)
|
100% |
320
3.80 IPS |
|
Face Detection (HP)
|
100% |
322
3.83 IPS |
|
Face Detection (Q)
|
97% |
725
8.64 IPS |
|
Depth Estimation (SP)
|
100% |
277
2.13 IPS |
|
Depth Estimation (HP)
|
100% |
276
2.13 IPS |
|
Depth Estimation (Q)
|
73% |
756
6.19 IPS |
|
Style Transfer (SP)
|
100% |
477
0.61 IPS |
|
Style Transfer (HP)
|
100% |
478
0.61 IPS |
|
Style Transfer (Q)
|
98% |
1324
1.71 IPS |
|
Image Super-Resolution (SP)
|
100% |
74
2.74 IPS |
|
Image Super-Resolution (HP)
|
100% |
846
31.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
483
17.9 IPS |
|
Text Classification (SP)
|
100% |
176
235.5 IPS |
|
Text Classification (HP)
|
100% |
177
235.9 IPS |
|
Text Classification (Q)
|
91% |
343
461.6 IPS |
|
Machine Translation (SP)
|
100% |
296
5.10 IPS |
|
Machine Translation (HP)
|
100% |
299
5.15 IPS |
|
Machine Translation (Q)
|
57% |
280
6.85 IPS |