Upload Date | December 28 2024 01:53 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM Unisoc |
System Information | |
---|---|
Operating System | Android 13 |
Model | TECNO TECNO BG6 |
Model ID | TECNO TECNO BG6 |
Motherboard | TECNO-BG6 |
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% |
167
31.1 IPS |
|
Image Classification (HP)
|
100% |
173
32.2 IPS |
|
Image Classification (Q)
|
100% |
445
82.8 IPS |
|
Image Segmentation (SP)
|
100% |
221
3.58 IPS |
|
Image Segmentation (HP)
|
100% |
212
3.44 IPS |
|
Image Segmentation (Q)
|
98% |
559
9.09 IPS |
|
Pose Estimation (SP)
|
100% |
801
0.93 IPS |
|
Pose Estimation (HP)
|
100% |
810
0.95 IPS |
|
Pose Estimation (Q)
|
84% |
1301
1.54 IPS |
|
Object Detection (SP)
|
100% |
193
15.3 IPS |
|
Object Detection (HP)
|
100% |
191
15.2 IPS |
|
Object Detection (Q)
|
83% |
404
32.6 IPS |
|
Face Detection (SP)
|
100% |
441
5.24 IPS |
|
Face Detection (HP)
|
100% |
446
5.30 IPS |
|
Face Detection (Q)
|
95% |
1049
12.5 IPS |
|
Depth Estimation (SP)
|
100% |
613
4.72 IPS |
|
Depth Estimation (HP)
|
99% |
608
4.69 IPS |
|
Depth Estimation (Q)
|
64% |
1127
10.3 IPS |
|
Style Transfer (SP)
|
89% |
1594
2.07 IPS |
|
Style Transfer (HP)
|
89% |
1616
2.10 IPS |
|
Style Transfer (Q)
|
98% |
3093
3.99 IPS |
|
Image Super-Resolution (SP)
|
100% |
310
11.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
310
11.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
630
23.3 IPS |
|
Text Classification (SP)
|
100% |
169
225.4 IPS |
|
Text Classification (HP)
|
100% |
167
222.3 IPS |
|
Text Classification (Q)
|
88% |
169
227.8 IPS |
|
Machine Translation (SP)
|
100% |
268
4.61 IPS |
|
Machine Translation (HP)
|
100% |
264
4.55 IPS |
|
Machine Translation (Q)
|
50% |
98
3.47 IPS |