User | benched |
Upload Date | October 08 2024 03:03 PM |
Views | 11 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM Samsung |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A047F |
Model ID | samsung SM-A047F |
Motherboard | exynos850 |
Governor | energy_step |
CPU Information | |
---|---|
Name | ARM Samsung |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3333 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 8 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 2.64 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
131
24.3 IPS |
|
Image Classification (HP)
|
100% |
130
24.3 IPS |
|
Image Classification (Q)
|
100% |
183
34.0 IPS |
|
Image Segmentation (SP)
|
100% |
186
3.01 IPS |
|
Image Segmentation (HP)
|
100% |
183
2.97 IPS |
|
Image Segmentation (Q)
|
98% |
262
4.27 IPS |
|
Pose Estimation (SP)
|
100% |
687
0.80 IPS |
|
Pose Estimation (HP)
|
100% |
681
0.79 IPS |
|
Pose Estimation (Q)
|
84% |
460
0.55 IPS |
|
Object Detection (SP)
|
100% |
149
11.8 IPS |
|
Object Detection (HP)
|
100% |
150
11.9 IPS |
|
Object Detection (Q)
|
83% |
181
14.6 IPS |
|
Face Detection (SP)
|
100% |
383
4.55 IPS |
|
Face Detection (HP)
|
100% |
373
4.43 IPS |
|
Face Detection (Q)
|
95% |
489
5.84 IPS |
|
Depth Estimation (SP)
|
100% |
486
3.75 IPS |
|
Depth Estimation (HP)
|
99% |
466
3.59 IPS |
|
Depth Estimation (Q)
|
64% |
468
4.28 IPS |
|
Style Transfer (SP)
|
89% |
1357
1.76 IPS |
|
Style Transfer (HP)
|
89% |
1367
1.77 IPS |
|
Style Transfer (Q)
|
98% |
1265
1.63 IPS |
|
Image Super-Resolution (SP)
|
100% |
269
9.94 IPS |
|
Image Super-Resolution (HP)
|
100% |
273
10.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
266
9.85 IPS |
|
Text Classification (SP)
|
100% |
136
182.0 IPS |
|
Text Classification (HP)
|
100% |
133
178.1 IPS |
|
Text Classification (Q)
|
88% |
147
197.7 IPS |
|
Machine Translation (SP)
|
100% |
214
3.68 IPS |
|
Machine Translation (HP)
|
100% |
210
3.61 IPS |
|
Machine Translation (Q)
|
50% |
86
3.06 IPS |