Upload Date | December 06 2024 12:02 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | INFINIX Infinix X6528B |
Model ID | INFINIX Infinix X6528B |
Motherboard | Infinix-X6528B |
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 |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
80
15.0 IPS |
|
Image Classification (F16)
|
100% |
79
14.9 IPS |
|
Image Classification (I8)
|
99% |
107
20.1 IPS |
|
Image Segmentation (F32)
|
100% |
99
1.65 IPS |
|
Image Segmentation (F16)
|
100% |
98
1.64 IPS |
|
Image Segmentation (I8)
|
98% |
136
2.27 IPS |
|
Pose Estimation (F32)
|
100% |
449
0.54 IPS |
|
Pose Estimation (F16)
|
100% |
448
0.54 IPS |
|
Pose Estimation (I8)
|
100% |
415
0.50 IPS |
|
Object Detection (F32)
|
100% |
43
3.24 IPS |
|
Object Detection (F16)
|
100% |
43
3.24 IPS |
|
Object Detection (I8)
|
61% |
82
6.10 IPS |
|
Face Detection (F32)
|
100% |
263
3.13 IPS |
|
Face Detection (F16)
|
100% |
262
3.11 IPS |
|
Face Detection (I8)
|
86% |
204
2.43 IPS |
|
Depth Estimation (F32)
|
100% |
364
2.82 IPS |
|
Depth Estimation (F16)
|
100% |
365
2.83 IPS |
|
Depth Estimation (I8)
|
96% |
391
3.03 IPS |
|
Style Transfer (F32)
|
100% |
323
0.43 IPS |
|
Style Transfer (F16)
|
100% |
326
0.43 IPS |
|
Style Transfer (I8)
|
97% |
548
0.72 IPS |
|
Image Super-Resolution (F32)
|
100% |
207
7.39 IPS |
|
Image Super-Resolution (F16)
|
100% |
207
7.41 IPS |
|
Image Super-Resolution (I8)
|
98% |
221
7.90 IPS |
|
Text Classification (F32)
|
100% |
20
28.6 IPS |
|
Text Classification (F16)
|
100% |
20
28.7 IPS |
|
Text Classification (I8)
|
94% |
25
36.6 IPS |
|
Machine Translation (F32)
|
100% |
72
1.33 IPS |
|
Machine Translation (F16)
|
100% |
103
1.90 IPS |
|
Machine Translation (I8)
|
57% |
71
1.31 IPS |