Upload Date | January 02 2025 07:12 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6769V/CU |
System Information | |
---|---|
Operating System | Android 13 |
Model | vivo V2109 |
Model ID | vivo V2109 |
Motherboard | k69v1_64 |
CPU Information | |
---|---|
Name | ARM MT6769V/CU |
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 | 3.63 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
99
18.4 IPS |
|
Image Classification (HP)
|
100% |
92
17.2 IPS |
|
Image Classification (Q)
|
100% |
194
36.0 IPS |
|
Image Segmentation (SP)
|
100% |
118
1.91 IPS |
|
Image Segmentation (HP)
|
100% |
119
1.93 IPS |
|
Image Segmentation (Q)
|
98% |
249
4.04 IPS |
|
Pose Estimation (SP)
|
100% |
480
0.56 IPS |
|
Pose Estimation (HP)
|
100% |
485
0.57 IPS |
|
Pose Estimation (Q)
|
84% |
412
0.49 IPS |
|
Object Detection (SP)
|
100% |
92
7.31 IPS |
|
Object Detection (HP)
|
100% |
92
7.27 IPS |
|
Object Detection (Q)
|
83% |
193
15.6 IPS |
|
Face Detection (SP)
|
100% |
289
3.44 IPS |
|
Face Detection (HP)
|
100% |
294
3.49 IPS |
|
Face Detection (Q)
|
95% |
516
6.16 IPS |
|
Depth Estimation (SP)
|
100% |
395
3.04 IPS |
|
Depth Estimation (HP)
|
99% |
395
3.04 IPS |
|
Depth Estimation (Q)
|
64% |
435
3.99 IPS |
|
Style Transfer (SP)
|
89% |
790
1.03 IPS |
|
Style Transfer (HP)
|
89% |
787
1.02 IPS |
|
Style Transfer (Q)
|
98% |
1062
1.37 IPS |
|
Image Super-Resolution (SP)
|
100% |
219
8.09 IPS |
|
Image Super-Resolution (HP)
|
100% |
210
7.75 IPS |
|
Image Super-Resolution (Q)
|
97% |
223
8.27 IPS |
|
Text Classification (SP)
|
100% |
109
145.6 IPS |
|
Text Classification (HP)
|
100% |
107
143.0 IPS |
|
Text Classification (Q)
|
88% |
172
232.3 IPS |
|
Machine Translation (SP)
|
100% |
211
3.63 IPS |
|
Machine Translation (HP)
|
100% |
208
3.58 IPS |
|
Machine Translation (Q)
|
50% |
136
4.81 IPS |