Upload Date | April 24 2025 01:00 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM Unisoc |
System Information | |
---|---|
Operating System | Android 13 |
Model | TECNO TECNO BG6i |
Model ID | TECNO TECNO BG6i |
Motherboard | TECNO-BG6i |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Unisoc |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.61 GHz |
Cluster 1 | 8 Cores @ 1.61 GHz |
Memory Information | |
---|---|
Size | 2.70 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
144
26.7 IPS |
|
Image Classification (HP)
|
100% |
165
30.8 IPS |
|
Image Classification (Q)
|
100% |
418
77.7 IPS |
|
Image Segmentation (SP)
|
100% |
217
3.52 IPS |
|
Image Segmentation (HP)
|
100% |
203
3.29 IPS |
|
Image Segmentation (Q)
|
98% |
544
8.85 IPS |
|
Pose Estimation (SP)
|
100% |
806
0.94 IPS |
|
Pose Estimation (HP)
|
100% |
795
0.93 IPS |
|
Pose Estimation (Q)
|
84% |
1283
1.52 IPS |
|
Object Detection (SP)
|
100% |
157
12.4 IPS |
|
Object Detection (HP)
|
100% |
182
14.4 IPS |
|
Object Detection (Q)
|
83% |
374
30.3 IPS |
|
Face Detection (SP)
|
100% |
440
5.22 IPS |
|
Face Detection (HP)
|
100% |
433
5.14 IPS |
|
Face Detection (Q)
|
95% |
995
11.9 IPS |
|
Depth Estimation (SP)
|
100% |
577
4.45 IPS |
|
Depth Estimation (HP)
|
99% |
580
4.47 IPS |
|
Depth Estimation (Q)
|
64% |
1096
10.0 IPS |
|
Style Transfer (SP)
|
89% |
1544
2.00 IPS |
|
Style Transfer (HP)
|
89% |
1575
2.05 IPS |
|
Style Transfer (Q)
|
98% |
2985
3.85 IPS |
|
Image Super-Resolution (SP)
|
100% |
306
11.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
309
11.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
606
22.4 IPS |
|
Text Classification (SP)
|
100% |
151
201.7 IPS |
|
Text Classification (HP)
|
100% |
155
206.9 IPS |
|
Text Classification (Q)
|
88% |
158
213.5 IPS |
|
Machine Translation (SP)
|
100% |
246
4.24 IPS |
|
Machine Translation (HP)
|
100% |
244
4.20 IPS |
|
Machine Translation (Q)
|
50% |
91
3.24 IPS |