Upload Date | June 16 2025 01:33 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | HONOR ALT-LX2 |
Model ID | HONOR ALT-LX2 |
Motherboard | ALTL |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3337 revision 0 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores @ 1.90 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
36
6.68 IPS |
|
Image Classification (HP)
|
100% |
72
13.4 IPS |
|
Image Classification (Q)
|
97% |
73
13.6 IPS |
|
Image Segmentation (SP)
|
100% |
35
0.56 IPS |
|
Image Segmentation (HP)
|
100% |
117
1.90 IPS |
|
Image Segmentation (Q)
|
98% |
117
1.91 IPS |
|
Pose Estimation (SP)
|
100% |
61
0.07 IPS |
|
Pose Estimation (HP)
|
100% |
124
0.14 IPS |
|
Pose Estimation (Q)
|
95% |
123
0.14 IPS |
|
Object Detection (SP)
|
100% |
36
2.87 IPS |
|
Object Detection (HP)
|
100% |
61
4.84 IPS |
|
Object Detection (Q)
|
89% |
60
4.81 IPS |
|
Face Detection (SP)
|
100% |
89
1.06 IPS |
|
Face Detection (HP)
|
100% |
224
2.66 IPS |
|
Face Detection (Q)
|
97% |
233
2.78 IPS |
|
Depth Estimation (SP)
|
100% |
82
0.63 IPS |
|
Depth Estimation (HP)
|
99% |
169
1.31 IPS |
|
Depth Estimation (Q)
|
63% |
138
1.30 IPS |
|
Style Transfer (SP)
|
100% |
172
0.22 IPS |
|
Style Transfer (HP)
|
100% |
323
0.42 IPS |
|
Style Transfer (Q)
|
98% |
321
0.41 IPS |
|
Image Super-Resolution (SP)
|
100% |
41
1.52 IPS |
|
Image Super-Resolution (HP)
|
100% |
84
3.11 IPS |
|
Image Super-Resolution (Q)
|
97% |
83
3.09 IPS |
|
Text Classification (SP)
|
100% |
82
108.9 IPS |
|
Text Classification (HP)
|
100% |
81
108.6 IPS |
|
Text Classification (Q)
|
91% |
107
143.8 IPS |
|
Machine Translation (SP)
|
100% |
137
2.37 IPS |
|
Machine Translation (HP)
|
100% |
142
2.45 IPS |
|
Machine Translation (Q)
|
57% |
106
2.60 IPS |