User | shimonocyou |
Upload Date | September 18 2024 10:35 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Sony SO-52D |
Model ID | Sony SO-52D |
Motherboard | holi |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 5.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
113
20.9 IPS |
|
Image Classification (HP)
|
100% |
113
21.0 IPS |
|
Image Classification (Q)
|
99% |
293
54.6 IPS |
|
Image Segmentation (SP)
|
100% |
154
2.50 IPS |
|
Image Segmentation (HP)
|
100% |
155
2.51 IPS |
|
Image Segmentation (Q)
|
98% |
344
5.59 IPS |
|
Pose Estimation (SP)
|
100% |
209
0.24 IPS |
|
Pose Estimation (HP)
|
100% |
208
0.24 IPS |
|
Pose Estimation (Q)
|
98% |
778
0.91 IPS |
|
Object Detection (SP)
|
100% |
112
8.85 IPS |
|
Object Detection (HP)
|
100% |
112
8.92 IPS |
|
Object Detection (Q)
|
87% |
309
24.8 IPS |
|
Face Detection (SP)
|
100% |
295
3.50 IPS |
|
Face Detection (HP)
|
100% |
297
3.53 IPS |
|
Face Detection (Q)
|
97% |
648
7.73 IPS |
|
Depth Estimation (SP)
|
100% |
256
1.97 IPS |
|
Depth Estimation (HP)
|
99% |
257
1.98 IPS |
|
Depth Estimation (Q)
|
64% |
601
5.45 IPS |
|
Style Transfer (SP)
|
100% |
439
0.56 IPS |
|
Style Transfer (HP)
|
100% |
440
0.57 IPS |
|
Style Transfer (Q)
|
98% |
1216
1.57 IPS |
|
Image Super-Resolution (SP)
|
100% |
124
4.58 IPS |
|
Image Super-Resolution (HP)
|
100% |
124
4.58 IPS |
|
Image Super-Resolution (Q)
|
97% |
428
15.9 IPS |
|
Text Classification (SP)
|
100% |
161
214.4 IPS |
|
Text Classification (HP)
|
100% |
160
214.1 IPS |
|
Text Classification (Q)
|
91% |
312
418.7 IPS |
|
Machine Translation (SP)
|
100% |
270
4.65 IPS |
|
Machine Translation (HP)
|
100% |
275
4.74 IPS |
|
Machine Translation (Q)
|
57% |
217
5.30 IPS |