User | aidanarcilla |
Upload Date | March 21 2025 01:47 PM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 2407FPN8EG |
Model ID | Xiaomi 2407FPN8EG |
Motherboard | rothko |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 3 Cores @ 2.85 GHz |
Cluster 3 | 1 Core @ 3.40 GHz |
Memory Information | |
---|---|
Size | 10.93 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
606
112.8 IPS |
|
Image Classification (HP)
|
100% |
4408
819.7 IPS |
|
Image Classification (Q)
|
99% |
8766
1.63 KIPS |
|
Image Segmentation (SP)
|
100% |
602
9.75 IPS |
|
Image Segmentation (HP)
|
100% |
4206
68.2 IPS |
|
Image Segmentation (Q)
|
98% |
1850
30.1 IPS |
|
Pose Estimation (SP)
|
100% |
7634
8.91 IPS |
|
Pose Estimation (HP)
|
100% |
18335
21.4 IPS |
|
Pose Estimation (Q)
|
95% |
74954
87.9 IPS |
|
Object Detection (SP)
|
100% |
532
42.2 IPS |
|
Object Detection (HP)
|
100% |
4693
372.3 IPS |
|
Object Detection (Q)
|
86% |
5704
458.8 IPS |
|
Face Detection (SP)
|
100% |
2735
32.5 IPS |
|
Face Detection (HP)
|
100% |
12096
143.7 IPS |
|
Face Detection (Q)
|
97% |
11680
139.3 IPS |
|
Depth Estimation (SP)
|
100% |
875
6.74 IPS |
|
Depth Estimation (HP)
|
99% |
19350
149.1 IPS |
|
Depth Estimation (Q)
|
62% |
33195
315.2 IPS |
|
Style Transfer (SP)
|
100% |
2394
3.08 IPS |
|
Style Transfer (HP)
|
100% |
669
0.86 IPS |
|
Style Transfer (Q)
|
30% |
390
5.87 IPS |
|
Image Super-Resolution (SP)
|
100% |
2132
78.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
10689
394.7 IPS |
|
Image Super-Resolution (Q)
|
41% |
7822
1.14 KIPS |
|
Text Classification (SP)
|
100% |
72
96.5 IPS |
|
Text Classification (HP)
|
97% |
1949
2.61 KIPS |
|
Text Classification (Q)
|
73% |
1869
2.65 KIPS |
|
Machine Translation (SP)
|
100% |
326
5.62 IPS |
|
Machine Translation (HP)
|
100% |
1944
33.5 IPS |
|
Machine Translation (Q)
|
60% |
412
9.27 IPS |