Upload Date | August 16 2024 05:43 PM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 23049PCD8G |
Model ID | Xiaomi 23049PCD8G |
Motherboard | marble |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.50 GHz |
Cluster 3 | 1 Core @ 2.92 GHz |
Memory Information | |
---|---|
Size | 7.01 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
168
31.5 IPS |
|
Image Classification (F16)
|
100% |
169
31.7 IPS |
|
Image Classification (I8)
|
97% |
468
87.6 IPS |
|
Image Segmentation (F32)
|
100% |
214
3.57 IPS |
|
Image Segmentation (F16)
|
100% |
214
3.57 IPS |
|
Image Segmentation (I8)
|
98% |
495
8.27 IPS |
|
Pose Estimation (F32)
|
100% |
291
0.35 IPS |
|
Pose Estimation (F16)
|
100% |
294
0.36 IPS |
|
Pose Estimation (I8)
|
100% |
1178
1.43 IPS |
|
Object Detection (F32)
|
100% |
178
13.3 IPS |
|
Object Detection (F16)
|
100% |
178
13.3 IPS |
|
Object Detection (I8)
|
61% |
531
39.6 IPS |
|
Face Detection (F32)
|
100% |
458
5.45 IPS |
|
Face Detection (F16)
|
100% |
464
5.52 IPS |
|
Face Detection (I8)
|
86% |
1120
13.3 IPS |
|
Depth Estimation (F32)
|
100% |
388
3.01 IPS |
|
Depth Estimation (F16)
|
100% |
385
2.99 IPS |
|
Depth Estimation (I8)
|
95% |
1133
8.79 IPS |
|
Style Transfer (F32)
|
100% |
656
0.86 IPS |
|
Style Transfer (F16)
|
100% |
656
0.86 IPS |
|
Style Transfer (I8)
|
98% |
1683
2.21 IPS |
|
Image Super-Resolution (F32)
|
100% |
192
6.85 IPS |
|
Image Super-Resolution (F16)
|
100% |
194
6.93 IPS |
|
Image Super-Resolution (I8)
|
98% |
716
25.6 IPS |
|
Text Classification (F32)
|
100% |
234
336.1 IPS |
|
Text Classification (F16)
|
100% |
233
334.3 IPS |
|
Text Classification (I8)
|
92% |
420
604.2 IPS |
|
Machine Translation (F32)
|
100% |
410
7.54 IPS |
|
Machine Translation (F16)
|
100% |
419
7.71 IPS |
|
Machine Translation (I8)
|
64% |
512
9.43 IPS |