Upload Date | September 18 2024 12:55 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM Unisoc |
System Information | |
---|---|
Operating System | Android 13 |
Model | TECNO TECNO BG6s |
Model ID | TECNO TECNO BG6s |
Motherboard | TECNO-BG6s |
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% |
88
16.3 IPS |
|
Image Classification (HP)
|
100% |
180
33.4 IPS |
|
Image Classification (Q)
|
100% |
184
34.1 IPS |
|
Image Segmentation (SP)
|
100% |
186
3.02 IPS |
|
Image Segmentation (HP)
|
100% |
191
3.10 IPS |
|
Image Segmentation (Q)
|
98% |
454
7.38 IPS |
|
Pose Estimation (SP)
|
100% |
772
0.90 IPS |
|
Pose Estimation (HP)
|
100% |
793
0.93 IPS |
|
Pose Estimation (Q)
|
84% |
1284
1.52 IPS |
|
Object Detection (SP)
|
100% |
194
15.4 IPS |
|
Object Detection (HP)
|
100% |
178
14.1 IPS |
|
Object Detection (Q)
|
83% |
404
32.7 IPS |
|
Face Detection (SP)
|
100% |
435
5.17 IPS |
|
Face Detection (HP)
|
100% |
458
5.45 IPS |
|
Face Detection (Q)
|
95% |
1042
12.4 IPS |
|
Depth Estimation (SP)
|
100% |
622
4.79 IPS |
|
Depth Estimation (HP)
|
99% |
581
4.48 IPS |
|
Depth Estimation (Q)
|
64% |
1126
10.3 IPS |
|
Style Transfer (SP)
|
89% |
1629
2.11 IPS |
|
Style Transfer (HP)
|
89% |
1627
2.11 IPS |
|
Style Transfer (Q)
|
98% |
3070
3.96 IPS |
|
Image Super-Resolution (SP)
|
100% |
319
11.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
327
12.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
609
22.6 IPS |
|
Text Classification (SP)
|
100% |
171
228.5 IPS |
|
Text Classification (HP)
|
100% |
167
222.5 IPS |
|
Text Classification (Q)
|
88% |
178
240.2 IPS |
|
Machine Translation (SP)
|
100% |
277
4.78 IPS |
|
Machine Translation (HP)
|
100% |
268
4.62 IPS |
|
Machine Translation (Q)
|
50% |
100
3.57 IPS |