Upload Date | December 27 2024 07:45 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | vivo V2408A |
Model ID | vivo V2408A |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 14.76 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1320
245.5 IPS |
|
Image Classification (HP)
|
100% |
1334
248.0 IPS |
|
Image Classification (Q)
|
100% |
2820
524.4 IPS |
|
Image Segmentation (SP)
|
100% |
1632
26.5 IPS |
|
Image Segmentation (HP)
|
100% |
1613
26.2 IPS |
|
Image Segmentation (Q)
|
98% |
3503
57.0 IPS |
|
Pose Estimation (SP)
|
100% |
3911
4.56 IPS |
|
Pose Estimation (HP)
|
100% |
3971
4.63 IPS |
|
Pose Estimation (Q)
|
84% |
10096
12.0 IPS |
|
Object Detection (SP)
|
98% |
1225
97.5 IPS |
|
Object Detection (HP)
|
98% |
1240
98.7 IPS |
|
Object Detection (Q)
|
83% |
2807
226.7 IPS |
|
Face Detection (SP)
|
100% |
3397
40.4 IPS |
|
Face Detection (HP)
|
100% |
3433
40.8 IPS |
|
Face Detection (Q)
|
95% |
6662
79.5 IPS |
|
Depth Estimation (SP)
|
99% |
3428
26.5 IPS |
|
Depth Estimation (HP)
|
99% |
3441
26.6 IPS |
|
Depth Estimation (Q)
|
64% |
6462
59.2 IPS |
|
Style Transfer (SP)
|
89% |
7808
10.1 IPS |
|
Style Transfer (HP)
|
89% |
7648
9.93 IPS |
|
Style Transfer (Q)
|
98% |
15563
20.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
1535
56.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
1535
56.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
3136
116.2 IPS |
|
Text Classification (SP)
|
100% |
651
869.5 IPS |
|
Text Classification (HP)
|
99% |
652
870.3 IPS |
|
Text Classification (Q)
|
88% |
472
636.0 IPS |
|
Machine Translation (SP)
|
100% |
985
17.0 IPS |
|
Machine Translation (HP)
|
100% |
999
17.2 IPS |
|
Machine Translation (Q)
|
50% |
395
14.0 IPS |