Upload Date | December 13 2024 07:17 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | vivo I2401 |
Model ID | vivo I2401 |
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 | 10.87 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1465
272.5 IPS |
|
Image Classification (HP)
|
100% |
1924
357.9 IPS |
|
Image Classification (Q)
|
100% |
4321
803.6 IPS |
|
Image Segmentation (SP)
|
100% |
2328
37.7 IPS |
|
Image Segmentation (HP)
|
100% |
2317
37.6 IPS |
|
Image Segmentation (Q)
|
98% |
3874
63.0 IPS |
|
Pose Estimation (SP)
|
100% |
5393
6.29 IPS |
|
Pose Estimation (HP)
|
100% |
5343
6.23 IPS |
|
Pose Estimation (Q)
|
84% |
14204
16.8 IPS |
|
Object Detection (SP)
|
98% |
1450
115.4 IPS |
|
Object Detection (HP)
|
98% |
1459
116.1 IPS |
|
Object Detection (Q)
|
83% |
3368
272.0 IPS |
|
Face Detection (SP)
|
100% |
3887
46.2 IPS |
|
Face Detection (HP)
|
100% |
3909
46.5 IPS |
|
Face Detection (Q)
|
95% |
7913
94.5 IPS |
|
Depth Estimation (SP)
|
99% |
4110
31.8 IPS |
|
Depth Estimation (HP)
|
99% |
3989
30.8 IPS |
|
Depth Estimation (Q)
|
64% |
8430
77.2 IPS |
|
Style Transfer (SP)
|
89% |
10001
13.0 IPS |
|
Style Transfer (HP)
|
89% |
9992
13.0 IPS |
|
Style Transfer (Q)
|
98% |
21575
27.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
2027
74.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
2032
75.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
4869
180.4 IPS |
|
Text Classification (SP)
|
100% |
838
1.12 KIPS |
|
Text Classification (HP)
|
99% |
831
1.11 KIPS |
|
Text Classification (Q)
|
88% |
883
1.19 KIPS |
|
Machine Translation (SP)
|
100% |
1174
20.2 IPS |
|
Machine Translation (HP)
|
100% |
1201
20.7 IPS |
|
Machine Translation (Q)
|
50% |
486
17.2 IPS |