Upload Date | January 06 2025 11:50 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 2410DPN6CC |
Model ID | Xiaomi 2410DPN6CC |
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 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 14.76 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
653
121.4 IPS |
|
Image Classification (HP)
|
100% |
1718
319.4 IPS |
|
Image Classification (Q)
|
99% |
1605
299.4 IPS |
|
Image Segmentation (SP)
|
100% |
1513
24.5 IPS |
|
Image Segmentation (HP)
|
100% |
3369
54.6 IPS |
|
Image Segmentation (Q)
|
98% |
3116
50.7 IPS |
|
Pose Estimation (SP)
|
100% |
1461
1.70 IPS |
|
Pose Estimation (HP)
|
100% |
2494
2.91 IPS |
|
Pose Estimation (Q)
|
96% |
2485
2.91 IPS |
|
Object Detection (SP)
|
100% |
500
39.7 IPS |
|
Object Detection (HP)
|
100% |
1225
97.1 IPS |
|
Object Detection (Q)
|
86% |
1220
98.0 IPS |
|
Face Detection (SP)
|
100% |
2800
33.3 IPS |
|
Face Detection (HP)
|
100% |
5758
68.4 IPS |
|
Face Detection (Q)
|
97% |
3806
45.4 IPS |
|
Depth Estimation (SP)
|
100% |
1470
11.3 IPS |
|
Depth Estimation (HP)
|
99% |
4110
31.8 IPS |
|
Depth Estimation (Q)
|
63% |
3402
31.6 IPS |
|
Style Transfer (SP)
|
100% |
5151
6.62 IPS |
|
Style Transfer (HP)
|
100% |
11033
14.2 IPS |
|
Style Transfer (Q)
|
98% |
10964
14.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
639
23.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
1938
71.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1912
70.8 IPS |
|
Text Classification (SP)
|
100% |
430
573.8 IPS |
|
Text Classification (HP)
|
100% |
432
576.5 IPS |
|
Text Classification (Q)
|
91% |
670
900.2 IPS |
|
Machine Translation (SP)
|
100% |
833
14.3 IPS |
|
Machine Translation (HP)
|
100% |
838
14.4 IPS |
|
Machine Translation (Q)
|
57% |
625
15.3 IPS |