Upload Date | November 20 2024 05:00 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 | 10.86 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
202
37.9 IPS |
|
Image Classification (F16)
|
100% |
134
25.0 IPS |
|
Image Classification (I8)
|
97% |
360
67.4 IPS |
|
Image Segmentation (F32)
|
100% |
266
4.44 IPS |
|
Image Segmentation (F16)
|
100% |
173
2.88 IPS |
|
Image Segmentation (I8)
|
98% |
363
6.06 IPS |
|
Pose Estimation (F32)
|
100% |
370
0.45 IPS |
|
Pose Estimation (F16)
|
100% |
370
0.45 IPS |
|
Pose Estimation (I8)
|
100% |
1409
1.71 IPS |
|
Object Detection (F32)
|
100% |
215
16.1 IPS |
|
Object Detection (F16)
|
100% |
141
10.5 IPS |
|
Object Detection (I8)
|
61% |
604
45.1 IPS |
|
Face Detection (F32)
|
100% |
579
6.88 IPS |
|
Face Detection (F16)
|
100% |
579
6.88 IPS |
|
Face Detection (I8)
|
86% |
822
9.78 IPS |
|
Depth Estimation (F32)
|
100% |
488
3.78 IPS |
|
Depth Estimation (F16)
|
100% |
491
3.80 IPS |
|
Depth Estimation (I8)
|
95% |
1293
10.0 IPS |
|
Style Transfer (F32)
|
100% |
721
0.95 IPS |
|
Style Transfer (F16)
|
100% |
590
0.78 IPS |
|
Style Transfer (I8)
|
98% |
2276
2.99 IPS |
|
Image Super-Resolution (F32)
|
100% |
255
9.09 IPS |
|
Image Super-Resolution (F16)
|
100% |
254
9.06 IPS |
|
Image Super-Resolution (I8)
|
98% |
913
32.6 IPS |
|
Text Classification (F32)
|
100% |
297
426.5 IPS |
|
Text Classification (F16)
|
100% |
187
269.3 IPS |
|
Text Classification (I8)
|
92% |
457
656.7 IPS |
|
Machine Translation (F32)
|
100% |
547
10.1 IPS |
|
Machine Translation (F16)
|
100% |
552
10.2 IPS |
|
Machine Translation (I8)
|
64% |
555
10.2 IPS |