Upload Date | December 21 2024 03:13 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2312FPCA6G |
Model ID | Xiaomi 2312FPCA6G |
Motherboard | emerald |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.20 GHz |
Memory Information | |
---|---|
Size | 11.39 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
200
37.2 IPS |
|
Image Classification (HP)
|
100% |
195
36.3 IPS |
|
Image Classification (Q)
|
100% |
563
104.6 IPS |
|
Image Segmentation (SP)
|
100% |
253
4.11 IPS |
|
Image Segmentation (HP)
|
100% |
249
4.04 IPS |
|
Image Segmentation (Q)
|
98% |
614
9.98 IPS |
|
Pose Estimation (SP)
|
100% |
983
1.15 IPS |
|
Pose Estimation (HP)
|
100% |
971
1.13 IPS |
|
Pose Estimation (Q)
|
84% |
1430
1.70 IPS |
|
Object Detection (SP)
|
100% |
199
15.8 IPS |
|
Object Detection (HP)
|
100% |
199
15.8 IPS |
|
Object Detection (Q)
|
83% |
545
44.0 IPS |
|
Face Detection (SP)
|
100% |
648
7.70 IPS |
|
Face Detection (HP)
|
100% |
647
7.68 IPS |
|
Face Detection (Q)
|
95% |
1261
15.1 IPS |
|
Depth Estimation (SP)
|
100% |
829
6.39 IPS |
|
Depth Estimation (HP)
|
99% |
834
6.42 IPS |
|
Depth Estimation (Q)
|
64% |
1280
11.7 IPS |
|
Style Transfer (SP)
|
89% |
1657
2.15 IPS |
|
Style Transfer (HP)
|
89% |
1655
2.15 IPS |
|
Style Transfer (Q)
|
98% |
3216
4.15 IPS |
|
Image Super-Resolution (SP)
|
100% |
424
15.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
443
16.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
785
29.1 IPS |
|
Text Classification (SP)
|
100% |
229
305.6 IPS |
|
Text Classification (HP)
|
100% |
235
313.2 IPS |
|
Text Classification (Q)
|
88% |
412
556.0 IPS |
|
Machine Translation (SP)
|
100% |
415
7.15 IPS |
|
Machine Translation (HP)
|
100% |
425
7.32 IPS |
|
Machine Translation (Q)
|
50% |
306
10.9 IPS |