Upload Date | September 19 2024 06:06 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | vivo V2338 |
Model ID | vivo V2338 |
Motherboard | parrot |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 5.33 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
33
6.06 IPS |
|
Image Classification (HP)
|
100% |
32
5.96 IPS |
|
Image Classification (Q)
|
99% |
97
18.0 IPS |
|
Image Segmentation (SP)
|
100% |
42
0.68 IPS |
|
Image Segmentation (HP)
|
100% |
43
0.69 IPS |
|
Image Segmentation (Q)
|
98% |
85
1.38 IPS |
|
Pose Estimation (SP)
|
100% |
56
0.07 IPS |
|
Pose Estimation (HP)
|
100% |
55
0.06 IPS |
|
Pose Estimation (Q)
|
98% |
256
0.30 IPS |
|
Object Detection (SP)
|
100% |
32
2.56 IPS |
|
Object Detection (HP)
|
100% |
33
2.65 IPS |
|
Object Detection (Q)
|
87% |
106
8.51 IPS |
|
Face Detection (SP)
|
100% |
78
0.92 IPS |
|
Face Detection (HP)
|
100% |
80
0.95 IPS |
|
Face Detection (Q)
|
97% |
208
2.48 IPS |
|
Depth Estimation (SP)
|
100% |
71
0.55 IPS |
|
Depth Estimation (HP)
|
99% |
71
0.55 IPS |
|
Depth Estimation (Q)
|
64% |
179
1.62 IPS |
|
Style Transfer (SP)
|
100% |
135
0.17 IPS |
|
Style Transfer (HP)
|
100% |
140
0.18 IPS |
|
Style Transfer (Q)
|
98% |
380
0.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
40
1.48 IPS |
|
Image Super-Resolution (HP)
|
100% |
38
1.40 IPS |
|
Image Super-Resolution (Q)
|
97% |
139
5.14 IPS |
|
Text Classification (SP)
|
100% |
48
63.8 IPS |
|
Text Classification (HP)
|
100% |
49
65.7 IPS |
|
Text Classification (Q)
|
91% |
93
125.5 IPS |
|
Machine Translation (SP)
|
100% |
85
1.46 IPS |
|
Machine Translation (HP)
|
100% |
84
1.45 IPS |
|
Machine Translation (Q)
|
57% |
74
1.80 IPS |