Upload Date | May 10 2025 04:08 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6769H |
System Information | |
---|---|
Operating System | Android 13 |
Model | TECNO TECNO KI7 |
Model ID | TECNO TECNO KI7 |
Motherboard | TECNO-KI7 |
CPU Information | |
---|---|
Name | ARM MT6769H |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 7.55 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
178
33.0 IPS |
|
Image Classification (HP)
|
100% |
183
34.0 IPS |
|
Image Classification (Q)
|
100% |
539
100.2 IPS |
|
Image Segmentation (SP)
|
100% |
205
3.32 IPS |
|
Image Segmentation (HP)
|
100% |
204
3.31 IPS |
|
Image Segmentation (Q)
|
98% |
652
10.6 IPS |
|
Pose Estimation (SP)
|
100% |
809
0.94 IPS |
|
Pose Estimation (HP)
|
100% |
740
0.86 IPS |
|
Pose Estimation (Q)
|
84% |
1345
1.60 IPS |
|
Object Detection (SP)
|
100% |
176
13.9 IPS |
|
Object Detection (HP)
|
100% |
175
13.9 IPS |
|
Object Detection (Q)
|
83% |
409
33.0 IPS |
|
Face Detection (SP)
|
100% |
435
5.16 IPS |
|
Face Detection (HP)
|
100% |
417
4.96 IPS |
|
Face Detection (Q)
|
95% |
1082
12.9 IPS |
|
Depth Estimation (SP)
|
100% |
520
4.01 IPS |
|
Depth Estimation (HP)
|
99% |
527
4.06 IPS |
|
Depth Estimation (Q)
|
64% |
994
9.11 IPS |
|
Style Transfer (SP)
|
89% |
1334
1.73 IPS |
|
Style Transfer (HP)
|
89% |
1341
1.74 IPS |
|
Style Transfer (Q)
|
98% |
2479
3.20 IPS |
|
Image Super-Resolution (SP)
|
100% |
274
10.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
266
9.81 IPS |
|
Image Super-Resolution (Q)
|
97% |
575
21.3 IPS |
|
Text Classification (SP)
|
100% |
170
226.5 IPS |
|
Text Classification (HP)
|
100% |
166
221.0 IPS |
|
Text Classification (Q)
|
88% |
208
280.3 IPS |
|
Machine Translation (SP)
|
100% |
224
3.85 IPS |
|
Machine Translation (HP)
|
100% |
229
3.94 IPS |
|
Machine Translation (Q)
|
50% |
116
4.11 IPS |