User | epicgeek |
Upload Date | November 26 2024 09:35 PM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | HONOR ALI-NX3 |
Model ID | HONOR ALI-NX3 |
Motherboard | parrot |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.28 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
30
5.57 IPS |
|
Image Classification (HP)
|
100% |
30
5.61 IPS |
|
Image Classification (Q)
|
99% |
93
17.3 IPS |
|
Image Segmentation (SP)
|
100% |
41
0.66 IPS |
|
Image Segmentation (HP)
|
100% |
41
0.66 IPS |
|
Image Segmentation (Q)
|
98% |
83
1.35 IPS |
|
Pose Estimation (SP)
|
100% |
49
0.06 IPS |
|
Pose Estimation (HP)
|
100% |
46
0.05 IPS |
|
Pose Estimation (Q)
|
98% |
249
0.29 IPS |
|
Object Detection (SP)
|
100% |
31
2.47 IPS |
|
Object Detection (HP)
|
100% |
31
2.48 IPS |
|
Object Detection (Q)
|
87% |
103
8.28 IPS |
|
Face Detection (SP)
|
100% |
73
0.87 IPS |
|
Face Detection (HP)
|
100% |
74
0.88 IPS |
|
Face Detection (Q)
|
97% |
195
2.32 IPS |
|
Depth Estimation (SP)
|
100% |
67
0.51 IPS |
|
Depth Estimation (HP)
|
99% |
67
0.51 IPS |
|
Depth Estimation (Q)
|
64% |
173
1.57 IPS |
|
Style Transfer (SP)
|
100% |
130
0.17 IPS |
|
Style Transfer (HP)
|
100% |
130
0.17 IPS |
|
Style Transfer (Q)
|
98% |
358
0.46 IPS |
|
Image Super-Resolution (SP)
|
100% |
39
1.42 IPS |
|
Image Super-Resolution (HP)
|
100% |
39
1.43 IPS |
|
Image Super-Resolution (Q)
|
97% |
137
5.08 IPS |
|
Text Classification (SP)
|
100% |
48
64.2 IPS |
|
Text Classification (HP)
|
100% |
48
64.2 IPS |
|
Text Classification (Q)
|
91% |
93
125.2 IPS |
|
Machine Translation (SP)
|
100% |
84
1.44 IPS |
|
Machine Translation (HP)
|
100% |
84
1.45 IPS |
|
Machine Translation (Q)
|
57% |
75
1.84 IPS |