Upload Date | September 26 2022 12:39 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | HONOR LGE-NX9 |
Model ID | HONOR LGE-NX9 |
Motherboard | taro |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.50 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 6.93 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1443
154.7 IPS |
|
Image Classification (F16)
|
100% |
2356
252.4 IPS |
|
Image Classification (I8)
|
80% |
2140
229.2 IPS |
|
Image Segmentation (F32)
|
100% |
4018
24.8 IPS |
|
Image Segmentation (F16)
|
100% |
6731
41.6 IPS |
|
Image Segmentation (I8)
|
89% |
5967
36.9 IPS |
|
Pose Estimation (F32)
|
100% |
2007
8.12 IPS |
|
Pose Estimation (F16)
|
100% |
3833
15.5 IPS |
|
Pose Estimation (I8)
|
80% |
3789
15.3 IPS |
|
Object Detection (F32)
|
100% |
576
20.2 IPS |
|
Object Detection (F16)
|
99% |
699
24.5 IPS |
|
Object Detection (I8)
|
53% |
715
25.1 IPS |
|
Face Detection (F32)
|
100% |
2644
30.4 IPS |
|
Face Detection (F16)
|
97% |
4729
54.3 IPS |
|
Face Detection (I8)
|
75% |
4028
46.3 IPS |
|
Text Classification (F32)
|
100% |
717
283.6 IPS |
|
Text Classification (F16)
|
98% |
812
321.3 IPS |
|
Machine Translation (F32)
|
100% |
752
115.9 IPS |
|
Machine Translation (F16)
|
100% |
757
116.7 IPS |