Upload Date | July 26 2024 01:14 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | INFINIX Infinix X6517 |
Model ID | INFINIX Infinix X6517 |
Motherboard | X6517 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Unisoc |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3333 revision 0 |
Base Frequency | 1.20 GHz |
Cluster 1 | 4 Cores @ 1.20 GHz |
Cluster 2 | 4 Cores @ 1.60 GHz |
Memory Information | |
---|---|
Size | 2.79 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
83
15.5 IPS |
|
Image Classification (F16)
|
100% |
86
16.1 IPS |
|
Image Classification (I8)
|
97% |
167
31.3 IPS |
|
Image Segmentation (F32)
|
100% |
134
2.24 IPS |
|
Image Segmentation (F16)
|
100% |
134
2.23 IPS |
|
Image Segmentation (I8)
|
98% |
123
2.05 IPS |
|
Pose Estimation (F32)
|
100% |
77
0.09 IPS |
|
Pose Estimation (F16)
|
100% |
101
0.12 IPS |
|
Pose Estimation (I8)
|
100% |
568
0.69 IPS |
|
Object Detection (F32)
|
100% |
72
5.38 IPS |
|
Object Detection (F16)
|
100% |
95
7.10 IPS |
|
Object Detection (I8)
|
61% |
183
13.7 IPS |
|
Face Detection (F32)
|
100% |
213
2.53 IPS |
|
Face Detection (F16)
|
100% |
217
2.58 IPS |
|
Face Detection (I8)
|
86% |
353
4.19 IPS |
|
Depth Estimation (F32)
|
100% |
166
1.29 IPS |
|
Depth Estimation (F16)
|
100% |
176
1.37 IPS |
|
Depth Estimation (I8)
|
95% |
416
3.23 IPS |
|
Style Transfer (F32)
|
100% |
225
0.30 IPS |
|
Style Transfer (F16)
|
100% |
193
0.25 IPS |
|
Style Transfer (I8)
|
98% |
616
0.81 IPS |
|
Image Super-Resolution (F32)
|
100% |
67
2.39 IPS |
|
Image Super-Resolution (F16)
|
100% |
60
2.16 IPS |
|
Image Super-Resolution (I8)
|
98% |
102
3.65 IPS |
|
Text Classification (F32)
|
100% |
9
13.1 IPS |
|
Text Classification (F16)
|
100% |
7
10.4 IPS |
|
Text Classification (I8)
|
92% |
11
15.5 IPS |
|
Machine Translation (F32)
|
100% |
196
3.61 IPS |
|
Machine Translation (F16)
|
100% |
202
3.72 IPS |
|
Machine Translation (I8)
|
64% |
110
2.03 IPS |