Upload Date | November 21 2024 04:15 AM |
Views | 1 |
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 | 14.76 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
624
116.8 IPS |
|
Image Classification (F16)
|
100% |
1582
295.9 IPS |
|
Image Classification (I8)
|
100% |
790
147.9 IPS |
|
Image Segmentation (F32)
|
100% |
936
15.6 IPS |
|
Image Segmentation (F16)
|
100% |
1313
21.9 IPS |
|
Image Segmentation (I8)
|
98% |
1285
21.5 IPS |
|
Pose Estimation (F32)
|
100% |
1421
1.72 IPS |
|
Pose Estimation (F16)
|
100% |
2419
2.93 IPS |
|
Pose Estimation (I8)
|
100% |
2419
2.93 IPS |
|
Object Detection (F32)
|
100% |
432
32.3 IPS |
|
Object Detection (F16)
|
100% |
493
36.8 IPS |
|
Object Detection (I8)
|
59% |
471
35.2 IPS |
|
Face Detection (F32)
|
100% |
2759
32.8 IPS |
|
Face Detection (F16)
|
97% |
4060
48.3 IPS |
|
Face Detection (I8)
|
86% |
3859
45.9 IPS |
|
Depth Estimation (F32)
|
100% |
1441
11.2 IPS |
|
Depth Estimation (F16)
|
100% |
4071
31.6 IPS |
|
Depth Estimation (I8)
|
94% |
4046
31.4 IPS |
|
Style Transfer (F32)
|
100% |
4992
6.57 IPS |
|
Style Transfer (F16)
|
100% |
10564
13.9 IPS |
|
Style Transfer (I8)
|
98% |
10625
14.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
663
23.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
1142
40.8 IPS |
|
Image Super-Resolution (I8)
|
98% |
1146
40.9 IPS |
|
Text Classification (F32)
|
100% |
430
617.4 IPS |
|
Text Classification (F16)
|
100% |
430
617.3 IPS |
|
Text Classification (I8)
|
92% |
666
957.0 IPS |
|
Machine Translation (F32)
|
100% |
779
14.3 IPS |
|
Machine Translation (F16)
|
100% |
783
14.4 IPS |
|
Machine Translation (I8)
|
64% |
797
14.7 IPS |