User | epicgeek |
Upload Date | November 26 2024 08:23 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
124
23.1 IPS |
|
Image Classification (HP)
|
100% |
218
40.6 IPS |
|
Image Classification (Q)
|
97% |
207
38.7 IPS |
|
Image Segmentation (SP)
|
100% |
183
2.97 IPS |
|
Image Segmentation (HP)
|
100% |
228
3.70 IPS |
|
Image Segmentation (Q)
|
98% |
218
3.54 IPS |
|
Pose Estimation (SP)
|
100% |
177
0.21 IPS |
|
Pose Estimation (HP)
|
100% |
295
0.34 IPS |
|
Pose Estimation (Q)
|
95% |
292
0.34 IPS |
|
Object Detection (SP)
|
100% |
101
7.98 IPS |
|
Object Detection (HP)
|
100% |
131
10.4 IPS |
|
Object Detection (Q)
|
89% |
132
10.6 IPS |
|
Face Detection (SP)
|
100% |
367
4.36 IPS |
|
Face Detection (HP)
|
100% |
493
5.85 IPS |
|
Face Detection (Q)
|
97% |
467
5.57 IPS |
|
Depth Estimation (SP)
|
100% |
274
2.11 IPS |
|
Depth Estimation (HP)
|
99% |
451
3.49 IPS |
|
Depth Estimation (Q)
|
63% |
370
3.47 IPS |
|
Style Transfer (SP)
|
100% |
606
0.78 IPS |
|
Style Transfer (HP)
|
100% |
1220
1.57 IPS |
|
Style Transfer (Q)
|
98% |
1222
1.58 IPS |
|
Image Super-Resolution (SP)
|
100% |
109
4.02 IPS |
|
Image Super-Resolution (HP)
|
100% |
137
5.05 IPS |
|
Image Super-Resolution (Q)
|
97% |
134
4.98 IPS |
|
Text Classification (SP)
|
100% |
48
64.0 IPS |
|
Text Classification (HP)
|
100% |
48
64.5 IPS |
|
Text Classification (Q)
|
91% |
92
124.3 IPS |
|
Machine Translation (SP)
|
100% |
84
1.44 IPS |
|
Machine Translation (HP)
|
100% |
84
1.45 IPS |
|
Machine Translation (Q)
|
57% |
76
1.85 IPS |