Upload Date | September 17 2024 03:19 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Nothing A142 |
Model ID | Nothing A142 |
Motherboard | Pacman |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3405 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 11.16 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
267
49.6 IPS |
|
Image Classification (HP)
|
100% |
340
63.2 IPS |
|
Image Classification (Q)
|
99% |
267
49.8 IPS |
|
Image Segmentation (SP)
|
100% |
461
7.47 IPS |
|
Image Segmentation (HP)
|
100% |
616
9.99 IPS |
|
Image Segmentation (Q)
|
98% |
602
9.80 IPS |
|
Pose Estimation (SP)
|
100% |
354
0.41 IPS |
|
Pose Estimation (HP)
|
100% |
459
0.54 IPS |
|
Pose Estimation (Q)
|
96% |
454
0.53 IPS |
|
Object Detection (SP)
|
100% |
202
16.1 IPS |
|
Object Detection (HP)
|
100% |
262
20.8 IPS |
|
Object Detection (Q)
|
83% |
284
23.0 IPS |
|
Face Detection (SP)
|
100% |
830
9.86 IPS |
|
Face Detection (HP)
|
100% |
1003
11.9 IPS |
|
Face Detection (Q)
|
97% |
942
11.2 IPS |
|
Depth Estimation (SP)
|
100% |
627
4.83 IPS |
|
Depth Estimation (HP)
|
99% |
704
5.43 IPS |
|
Depth Estimation (Q)
|
62% |
563
5.33 IPS |
|
Style Transfer (SP)
|
100% |
1431
1.84 IPS |
|
Style Transfer (HP)
|
100% |
1779
2.29 IPS |
|
Style Transfer (Q)
|
98% |
1768
2.28 IPS |
|
Image Super-Resolution (SP)
|
100% |
261
9.64 IPS |
|
Image Super-Resolution (HP)
|
100% |
339
12.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
323
12.0 IPS |
|
Text Classification (SP)
|
100% |
141
188.7 IPS |
|
Text Classification (HP)
|
100% |
142
189.2 IPS |
|
Text Classification (Q)
|
91% |
289
389.1 IPS |
|
Machine Translation (SP)
|
100% |
217
3.73 IPS |
|
Machine Translation (HP)
|
100% |
220
3.79 IPS |
|
Machine Translation (Q)
|
57% |
174
4.25 IPS |