User | Benchmarker |
Upload Date | April 05 2025 04:25 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | TECNO TECNO KL4 |
Model ID | TECNO TECNO KL4 |
Motherboard | TECNO-KL4 |
Governor | uscfreq |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.61 GHz |
Cluster 1 | 6 Cores @ 1.61 GHz |
Cluster 2 | 2 Cores @ 1.82 GHz |
Memory Information | |
---|---|
Size | 2.72 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
96
17.9 IPS |
|
Image Classification (HP)
|
100% |
96
17.9 IPS |
|
Image Classification (Q)
|
100% |
199
37.1 IPS |
|
Image Segmentation (SP)
|
100% |
125
2.03 IPS |
|
Image Segmentation (HP)
|
100% |
125
2.03 IPS |
|
Image Segmentation (Q)
|
98% |
249
4.05 IPS |
|
Pose Estimation (SP)
|
100% |
506
0.59 IPS |
|
Pose Estimation (HP)
|
100% |
506
0.59 IPS |
|
Pose Estimation (Q)
|
84% |
382
0.45 IPS |
|
Object Detection (SP)
|
100% |
97
7.67 IPS |
|
Object Detection (HP)
|
100% |
97
7.68 IPS |
|
Object Detection (Q)
|
83% |
194
15.7 IPS |
|
Face Detection (SP)
|
100% |
332
3.94 IPS |
|
Face Detection (HP)
|
100% |
333
3.95 IPS |
|
Face Detection (Q)
|
95% |
553
6.61 IPS |
|
Depth Estimation (SP)
|
100% |
446
3.44 IPS |
|
Depth Estimation (HP)
|
99% |
436
3.36 IPS |
|
Depth Estimation (Q)
|
64% |
431
3.95 IPS |
|
Style Transfer (SP)
|
89% |
831
1.08 IPS |
|
Style Transfer (HP)
|
89% |
833
1.08 IPS |
|
Style Transfer (Q)
|
98% |
982
1.27 IPS |
|
Image Super-Resolution (SP)
|
100% |
237
8.75 IPS |
|
Image Super-Resolution (HP)
|
100% |
235
8.69 IPS |
|
Image Super-Resolution (Q)
|
97% |
237
8.79 IPS |
|
Text Classification (SP)
|
100% |
118
157.1 IPS |
|
Text Classification (HP)
|
100% |
117
156.2 IPS |
|
Text Classification (Q)
|
88% |
188
253.1 IPS |
|
Machine Translation (SP)
|
100% |
215
3.70 IPS |
|
Machine Translation (HP)
|
100% |
214
3.68 IPS |
|
Machine Translation (Q)
|
50% |
137
4.86 IPS |