Upload Date | September 19 2024 06:21 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2312DRA50G |
Model ID | Xiaomi 2312DRA50G |
Motherboard | garnet |
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 | 1.96 GHz |
Cluster 1 | 4 Cores @ 1.96 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.13 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
403
74.9 IPS |
|
Image Classification (HP)
|
100% |
405
75.3 IPS |
|
Image Classification (Q)
|
100% |
1245
231.6 IPS |
|
Image Segmentation (SP)
|
100% |
489
7.93 IPS |
|
Image Segmentation (HP)
|
100% |
491
7.96 IPS |
|
Image Segmentation (Q)
|
98% |
1454
23.6 IPS |
|
Pose Estimation (SP)
|
100% |
1862
2.17 IPS |
|
Pose Estimation (HP)
|
100% |
1796
2.10 IPS |
|
Pose Estimation (Q)
|
84% |
2987
3.54 IPS |
|
Object Detection (SP)
|
100% |
378
30.0 IPS |
|
Object Detection (HP)
|
100% |
378
30.0 IPS |
|
Object Detection (Q)
|
83% |
1133
91.5 IPS |
|
Face Detection (SP)
|
100% |
1022
12.1 IPS |
|
Face Detection (HP)
|
100% |
1018
12.1 IPS |
|
Face Detection (Q)
|
95% |
2780
33.2 IPS |
|
Depth Estimation (SP)
|
100% |
1437
11.1 IPS |
|
Depth Estimation (HP)
|
99% |
1421
11.0 IPS |
|
Depth Estimation (Q)
|
64% |
2736
25.1 IPS |
|
Style Transfer (SP)
|
89% |
3133
4.07 IPS |
|
Style Transfer (HP)
|
89% |
3115
4.04 IPS |
|
Style Transfer (Q)
|
98% |
6871
8.86 IPS |
|
Image Super-Resolution (SP)
|
100% |
280
10.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
285
10.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
676
25.1 IPS |
|
Text Classification (SP)
|
100% |
170
227.2 IPS |
|
Text Classification (HP)
|
100% |
170
227.6 IPS |
|
Text Classification (Q)
|
88% |
288
389.0 IPS |
|
Machine Translation (SP)
|
100% |
286
4.92 IPS |
|
Machine Translation (HP)
|
100% |
284
4.90 IPS |
|
Machine Translation (Q)
|
50% |
173
6.15 IPS |