Upload Date | December 27 2024 10:08 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | vivo V2309A |
Model ID | vivo V2309A |
Motherboard | k6989v1_64 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 3 Cores @ 2.85 GHz |
Cluster 3 | 1 Core @ 3.25 GHz |
Memory Information | |
---|---|
Size | 11.05 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
529
98.4 IPS |
|
Image Classification (HP)
|
100% |
661
122.9 IPS |
|
Image Classification (Q)
|
99% |
638
119.0 IPS |
|
Image Segmentation (SP)
|
100% |
1243
20.2 IPS |
|
Image Segmentation (HP)
|
100% |
1286
20.9 IPS |
|
Image Segmentation (Q)
|
98% |
1292
21.0 IPS |
|
Pose Estimation (SP)
|
100% |
699
0.82 IPS |
|
Pose Estimation (HP)
|
100% |
1052
1.23 IPS |
|
Pose Estimation (Q)
|
96% |
1043
1.22 IPS |
|
Object Detection (SP)
|
100% |
483
38.3 IPS |
|
Object Detection (HP)
|
100% |
641
50.8 IPS |
|
Object Detection (Q)
|
83% |
718
58.1 IPS |
|
Face Detection (SP)
|
100% |
2185
26.0 IPS |
|
Face Detection (HP)
|
100% |
2171
25.8 IPS |
|
Face Detection (Q)
|
97% |
1901
22.7 IPS |
|
Depth Estimation (SP)
|
100% |
1307
10.1 IPS |
|
Depth Estimation (HP)
|
99% |
1635
12.6 IPS |
|
Depth Estimation (Q)
|
62% |
1307
12.4 IPS |
|
Style Transfer (SP)
|
100% |
3855
4.96 IPS |
|
Style Transfer (HP)
|
100% |
4908
6.31 IPS |
|
Style Transfer (Q)
|
98% |
4900
6.32 IPS |
|
Image Super-Resolution (SP)
|
100% |
693
25.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
897
33.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
870
32.2 IPS |
|
Text Classification (SP)
|
100% |
207
275.9 IPS |
|
Text Classification (HP)
|
100% |
206
274.7 IPS |
|
Text Classification (Q)
|
91% |
397
533.0 IPS |
|
Machine Translation (SP)
|
100% |
334
5.76 IPS |
|
Machine Translation (HP)
|
100% |
336
5.79 IPS |
|
Machine Translation (Q)
|
57% |
347
8.49 IPS |