Upload Date | November 17 2024 09:18 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | HONOR REA-NX9 |
Model ID | HONOR REA-NX9 |
Motherboard | taro |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3399 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.36 GHz |
Cluster 3 | 1 Core @ 2.52 GHz |
Memory Information | |
---|---|
Size | 11.04 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
133
24.8 IPS |
|
Image Classification (HP)
|
100% |
134
24.9 IPS |
|
Image Classification (Q)
|
99% |
361
67.3 IPS |
|
Image Segmentation (SP)
|
100% |
180
2.91 IPS |
|
Image Segmentation (HP)
|
100% |
181
2.93 IPS |
|
Image Segmentation (Q)
|
98% |
395
6.42 IPS |
|
Pose Estimation (SP)
|
100% |
243
0.28 IPS |
|
Pose Estimation (HP)
|
100% |
243
0.28 IPS |
|
Pose Estimation (Q)
|
98% |
932
1.09 IPS |
|
Object Detection (SP)
|
100% |
133
10.6 IPS |
|
Object Detection (HP)
|
100% |
134
10.6 IPS |
|
Object Detection (Q)
|
87% |
390
31.3 IPS |
|
Face Detection (SP)
|
100% |
344
4.08 IPS |
|
Face Detection (HP)
|
100% |
346
4.11 IPS |
|
Face Detection (Q)
|
97% |
787
9.39 IPS |
|
Depth Estimation (SP)
|
100% |
297
2.29 IPS |
|
Depth Estimation (HP)
|
99% |
297
2.29 IPS |
|
Depth Estimation (Q)
|
64% |
738
6.70 IPS |
|
Style Transfer (SP)
|
100% |
514
0.66 IPS |
|
Style Transfer (HP)
|
100% |
514
0.66 IPS |
|
Style Transfer (Q)
|
98% |
1448
1.87 IPS |
|
Image Super-Resolution (SP)
|
100% |
148
5.45 IPS |
|
Image Super-Resolution (HP)
|
100% |
148
5.46 IPS |
|
Image Super-Resolution (Q)
|
97% |
532
19.7 IPS |
|
Text Classification (SP)
|
100% |
191
254.4 IPS |
|
Text Classification (HP)
|
100% |
190
254.0 IPS |
|
Text Classification (Q)
|
91% |
360
483.5 IPS |
|
Machine Translation (SP)
|
100% |
322
5.55 IPS |
|
Machine Translation (HP)
|
100% |
320
5.50 IPS |
|
Machine Translation (Q)
|
57% |
299
7.31 IPS |