Upload Date | August 22 2024 07:23 AM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM Unisoc |
System Information | |
---|---|
Operating System | Android 13 |
Model | INFINIX Infinix X6528 |
Model ID | INFINIX Infinix X6528 |
Motherboard | Infinix-X6528 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Unisoc |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.61 GHz |
Cluster 1 | 8 Cores @ 1.61 GHz |
Memory Information | |
---|---|
Size | 7.59 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
82
15.2 IPS |
|
Image Classification (HP)
|
100% |
81
15.1 IPS |
|
Image Classification (Q)
|
99% |
107
19.9 IPS |
|
Image Segmentation (SP)
|
100% |
103
1.67 IPS |
|
Image Segmentation (HP)
|
100% |
103
1.67 IPS |
|
Image Segmentation (Q)
|
98% |
141
2.30 IPS |
|
Pose Estimation (SP)
|
100% |
467
0.54 IPS |
|
Pose Estimation (HP)
|
100% |
467
0.54 IPS |
|
Pose Estimation (Q)
|
96% |
428
0.50 IPS |
|
Object Detection (SP)
|
100% |
42
3.29 IPS |
|
Object Detection (HP)
|
100% |
42
3.31 IPS |
|
Object Detection (Q)
|
89% |
79
6.29 IPS |
|
Face Detection (SP)
|
100% |
263
3.13 IPS |
|
Face Detection (HP)
|
100% |
263
3.12 IPS |
|
Face Detection (Q)
|
97% |
203
2.42 IPS |
|
Depth Estimation (SP)
|
100% |
370
2.85 IPS |
|
Depth Estimation (HP)
|
100% |
370
2.85 IPS |
|
Depth Estimation (Q)
|
82% |
386
3.04 IPS |
|
Style Transfer (SP)
|
100% |
332
0.43 IPS |
|
Style Transfer (HP)
|
100% |
188
0.24 IPS |
|
Style Transfer (Q)
|
98% |
564
0.73 IPS |
|
Image Super-Resolution (SP)
|
100% |
201
7.41 IPS |
|
Image Super-Resolution (HP)
|
100% |
201
7.42 IPS |
|
Image Super-Resolution (Q)
|
97% |
214
7.93 IPS |
|
Text Classification (SP)
|
100% |
26
34.4 IPS |
|
Text Classification (HP)
|
100% |
59
78.9 IPS |
|
Text Classification (Q)
|
93% |
30
40.2 IPS |
|
Machine Translation (SP)
|
100% |
73
1.25 IPS |
|
Machine Translation (HP)
|
100% |
104
1.78 IPS |
|
Machine Translation (Q)
|
55% |
49
1.29 IPS |