Upload Date | October 15 2024 11:46 PM |
Views | 5 |
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 | 3.62 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
140
26.1 IPS |
|
Image Classification (HP)
|
100% |
139
25.9 IPS |
|
Image Classification (Q)
|
100% |
197
36.7 IPS |
|
Image Segmentation (SP)
|
100% |
189
3.07 IPS |
|
Image Segmentation (HP)
|
100% |
189
3.07 IPS |
|
Image Segmentation (Q)
|
98% |
289
4.70 IPS |
|
Pose Estimation (SP)
|
100% |
737
0.86 IPS |
|
Pose Estimation (HP)
|
100% |
734
0.86 IPS |
|
Pose Estimation (Q)
|
84% |
451
0.53 IPS |
|
Object Detection (SP)
|
100% |
138
10.9 IPS |
|
Object Detection (HP)
|
100% |
141
11.2 IPS |
|
Object Detection (Q)
|
83% |
174
14.1 IPS |
|
Face Detection (SP)
|
100% |
356
4.23 IPS |
|
Face Detection (HP)
|
100% |
348
4.14 IPS |
|
Face Detection (Q)
|
95% |
467
5.57 IPS |
|
Depth Estimation (SP)
|
100% |
379
2.92 IPS |
|
Depth Estimation (HP)
|
99% |
396
3.05 IPS |
|
Depth Estimation (Q)
|
64% |
439
4.02 IPS |
|
Style Transfer (SP)
|
89% |
1312
1.70 IPS |
|
Style Transfer (HP)
|
89% |
1290
1.67 IPS |
|
Style Transfer (Q)
|
98% |
1234
1.59 IPS |
|
Image Super-Resolution (SP)
|
100% |
254
9.36 IPS |
|
Image Super-Resolution (HP)
|
100% |
258
9.53 IPS |
|
Image Super-Resolution (Q)
|
97% |
260
9.63 IPS |
|
Text Classification (SP)
|
100% |
123
163.9 IPS |
|
Text Classification (HP)
|
100% |
122
162.8 IPS |
|
Text Classification (Q)
|
88% |
136
183.4 IPS |
|
Machine Translation (SP)
|
100% |
201
3.46 IPS |
|
Machine Translation (HP)
|
100% |
194
3.33 IPS |
|
Machine Translation (Q)
|
50% |
82
2.89 IPS |