Upload Date | September 26 2022 12:45 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 | NNAPI |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1308
140.1 IPS |
|
Image Classification (F16)
|
100% |
9220
987.9 IPS |
|
Image Classification (I8)
|
80% |
22372
2.40 KIPS |
|
Image Segmentation (F32)
|
100% |
2745
17.0 IPS |
|
Image Segmentation (F16)
|
100% |
155
0.96 IPS |
|
Image Segmentation (I8)
|
89% |
41263
254.9 IPS |
|
Pose Estimation (F32)
|
100% |
606
2.45 IPS |
|
Pose Estimation (F16)
|
100% |
10294
41.7 IPS |
|
Pose Estimation (I8)
|
80% |
54903
222.2 IPS |
|
Object Detection (F32)
|
100% |
925
32.4 IPS |
|
Object Detection (F16)
|
100% |
1626
57.1 IPS |
|
Object Detection (I8)
|
53% |
1787
62.7 IPS |
|
Face Detection (F32)
|
100% |
1866
21.4 IPS |
|
Face Detection (F16)
|
100% |
569
6.54 IPS |
|
Face Detection (I8)
|
76% |
44382
509.9 IPS |
|
Text Classification (F32)
|
100% |
15
5.89 IPS |
|
Text Classification (F16)
|
100% |
355
140.6 IPS |
|
Machine Translation (F32)
|
100% |
890
137.2 IPS |
|
Machine Translation (F16)
|
100% |
916
141.2 IPS |