| Upload Date | November 01 2024 09:02 AM |
| Views | 53 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Qualcomm ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 15 |
| Model | Xiaomi 24129PN74G |
| Model ID | Xiaomi 24129PN74G |
| Motherboard | sun |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | Qualcomm ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 0 |
| Base Frequency | 2.78 GHz |
| Cluster 1 | 6 Cores @ 2.78 GHz |
| Cluster 2 | 2 Cores @ 4.09 GHz |
| Memory Information | |
|---|---|
| Size | 10.81 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1006
187.1 IPS |
|
|
Image Classification (HP)
|
100% |
1489
276.9 IPS |
|
|
Image Classification (Q)
|
100% |
2897
538.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
1852
30.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
1926
31.2 IPS |
|
|
Image Segmentation (Q)
|
98% |
3829
62.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
4317
5.04 IPS |
|
|
Pose Estimation (HP)
|
100% |
4250
4.96 IPS |
|
|
Pose Estimation (Q)
|
84% |
11267
13.4 IPS |
|
|
Object Detection (SP)
|
98% |
1374
109.4 IPS |
|
|
Object Detection (HP)
|
98% |
1385
110.2 IPS |
|
|
Object Detection (Q)
|
83% |
3120
252.1 IPS |
|
|
Face Detection (SP)
|
100% |
3686
43.8 IPS |
|
|
Face Detection (HP)
|
100% |
3569
42.4 IPS |
|
|
Face Detection (Q)
|
95% |
7080
84.5 IPS |
|
|
Depth Estimation (SP)
|
99% |
3547
27.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
3393
26.2 IPS |
|
|
Depth Estimation (Q)
|
64% |
7699
70.5 IPS |
|
|
Style Transfer (SP)
|
89% |
8843
11.5 IPS |
|
|
Style Transfer (HP)
|
89% |
9389
12.2 IPS |
|
|
Style Transfer (Q)
|
98% |
16986
21.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1633
60.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1635
60.4 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
4106
152.1 IPS |
|
|
Text Classification (SP)
|
100% |
601
802.7 IPS |
|
|
Text Classification (HP)
|
99% |
661
882.6 IPS |
|
|
Text Classification (Q)
|
88% |
587
791.7 IPS |
|
|
Machine Translation (SP)
|
100% |
1045
18.0 IPS |
|
|
Machine Translation (HP)
|
100% |
1046
18.0 IPS |
|
|
Machine Translation (Q)
|
50% |
418
14.8 IPS |