Upload Date | November 19 2024 10:57 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 24129PN74C |
Model ID | Xiaomi 24129PN74C |
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 | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
403
74.9 IPS |
|
Image Classification (HP)
|
100% |
408
75.8 IPS |
|
Image Classification (Q)
|
99% |
1067
199.1 IPS |
|
Image Segmentation (SP)
|
100% |
529
8.57 IPS |
|
Image Segmentation (HP)
|
100% |
531
8.60 IPS |
|
Image Segmentation (Q)
|
98% |
1044
17.0 IPS |
|
Pose Estimation (SP)
|
100% |
698
0.81 IPS |
|
Pose Estimation (HP)
|
100% |
630
0.73 IPS |
|
Pose Estimation (Q)
|
98% |
2496
2.92 IPS |
|
Object Detection (SP)
|
100% |
355
28.1 IPS |
|
Object Detection (HP)
|
100% |
358
28.4 IPS |
|
Object Detection (Q)
|
87% |
1096
87.9 IPS |
|
Face Detection (SP)
|
100% |
893
10.6 IPS |
|
Face Detection (HP)
|
100% |
896
10.6 IPS |
|
Face Detection (Q)
|
97% |
1968
23.5 IPS |
|
Depth Estimation (SP)
|
100% |
759
5.85 IPS |
|
Depth Estimation (HP)
|
99% |
759
5.85 IPS |
|
Depth Estimation (Q)
|
64% |
1806
16.4 IPS |
|
Style Transfer (SP)
|
100% |
1300
1.67 IPS |
|
Style Transfer (HP)
|
100% |
1269
1.63 IPS |
|
Style Transfer (Q)
|
98% |
3509
4.52 IPS |
|
Image Super-Resolution (SP)
|
100% |
400
14.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
404
14.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1490
55.2 IPS |
|
Text Classification (SP)
|
100% |
566
755.3 IPS |
|
Text Classification (HP)
|
100% |
566
755.9 IPS |
|
Text Classification (Q)
|
91% |
889
1.19 KIPS |
|
Machine Translation (SP)
|
100% |
890
15.3 IPS |
|
Machine Translation (HP)
|
100% |
870
15.0 IPS |
|
Machine Translation (Q)
|
57% |
661
16.2 IPS |