Upload Date | November 27 2024 04:06 PM |
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% |
651
121.9 IPS |
|
Image Classification (F16)
|
100% |
1511
282.8 IPS |
|
Image Classification (I8)
|
100% |
1591
297.7 IPS |
|
Image Segmentation (F32)
|
100% |
1000
16.7 IPS |
|
Image Segmentation (F16)
|
100% |
1508
25.2 IPS |
|
Image Segmentation (I8)
|
98% |
1405
23.5 IPS |
|
Pose Estimation (F32)
|
100% |
1431
1.73 IPS |
|
Pose Estimation (F16)
|
100% |
2421
2.93 IPS |
|
Pose Estimation (I8)
|
100% |
2432
2.95 IPS |
|
Object Detection (F32)
|
100% |
499
37.2 IPS |
|
Object Detection (F16)
|
100% |
494
36.9 IPS |
|
Object Detection (I8)
|
59% |
537
40.1 IPS |
|
Face Detection (F32)
|
100% |
2926
34.8 IPS |
|
Face Detection (F16)
|
97% |
5690
67.7 IPS |
|
Face Detection (I8)
|
86% |
5070
60.3 IPS |
|
Depth Estimation (F32)
|
100% |
1438
11.2 IPS |
|
Depth Estimation (F16)
|
100% |
4117
31.9 IPS |
|
Depth Estimation (I8)
|
94% |
4124
32.0 IPS |
|
Style Transfer (F32)
|
100% |
4133
5.44 IPS |
|
Style Transfer (F16)
|
100% |
10099
13.3 IPS |
|
Style Transfer (I8)
|
98% |
7558
9.94 IPS |
|
Image Super-Resolution (F32)
|
100% |
630
22.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
1204
43.0 IPS |
|
Image Super-Resolution (I8)
|
98% |
737
26.3 IPS |
|
Text Classification (F32)
|
100% |
186
267.1 IPS |
|
Text Classification (F16)
|
100% |
186
267.2 IPS |
|
Text Classification (I8)
|
92% |
309
443.7 IPS |
|
Machine Translation (F32)
|
100% |
728
13.4 IPS |
|
Machine Translation (F16)
|
100% |
726
13.4 IPS |
|
Machine Translation (I8)
|
64% |
746
13.7 IPS |