Upload Date | November 18 2024 02:29 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Nothing A015 |
Model ID | Nothing A015 |
Motherboard | Tetris |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.50 GHz |
Memory Information | |
---|---|
Size | 5.32 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
187
34.7 IPS |
|
Image Classification (HP)
|
100% |
235
43.8 IPS |
|
Image Classification (Q)
|
99% |
217
40.6 IPS |
|
Image Segmentation (SP)
|
100% |
362
5.87 IPS |
|
Image Segmentation (HP)
|
100% |
429
6.96 IPS |
|
Image Segmentation (Q)
|
98% |
417
6.79 IPS |
|
Pose Estimation (SP)
|
100% |
190
0.22 IPS |
|
Pose Estimation (HP)
|
100% |
254
0.30 IPS |
|
Pose Estimation (Q)
|
96% |
252
0.30 IPS |
|
Object Detection (SP)
|
100% |
154
12.2 IPS |
|
Object Detection (HP)
|
100% |
199
15.8 IPS |
|
Object Detection (Q)
|
83% |
220
17.8 IPS |
|
Face Detection (SP)
|
100% |
684
8.13 IPS |
|
Face Detection (HP)
|
100% |
808
9.60 IPS |
|
Face Detection (Q)
|
97% |
784
9.34 IPS |
|
Depth Estimation (SP)
|
100% |
384
2.96 IPS |
|
Depth Estimation (HP)
|
99% |
476
3.67 IPS |
|
Depth Estimation (Q)
|
62% |
386
3.66 IPS |
|
Style Transfer (SP)
|
100% |
999
1.28 IPS |
|
Style Transfer (HP)
|
100% |
1186
1.52 IPS |
|
Style Transfer (Q)
|
98% |
1178
1.52 IPS |
|
Image Super-Resolution (SP)
|
100% |
202
7.47 IPS |
|
Image Super-Resolution (HP)
|
100% |
229
8.45 IPS |
|
Image Super-Resolution (Q)
|
97% |
226
8.39 IPS |
|
Text Classification (SP)
|
100% |
115
153.0 IPS |
|
Text Classification (HP)
|
100% |
114
152.4 IPS |
|
Text Classification (Q)
|
91% |
289
388.1 IPS |
|
Machine Translation (SP)
|
100% |
191
3.28 IPS |
|
Machine Translation (HP)
|
100% |
191
3.28 IPS |
|
Machine Translation (Q)
|
57% |
218
5.32 IPS |