Upload Date | July 18 2024 03:55 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 11T Pro |
Model ID | Xiaomi 2107113SG |
Motherboard | vili |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Odin |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.05 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
562
105.1 IPS |
|
Image Classification (F16)
|
100% |
1108
207.3 IPS |
|
Image Classification (I8)
|
94% |
18
3.30 IPS |
|
Image Segmentation (F32)
|
100% |
931
15.5 IPS |
|
Image Segmentation (F16)
|
100% |
1618
27.0 IPS |
|
Image Segmentation (I8)
|
98% |
312
5.20 IPS |
|
Pose Estimation (F32)
|
100% |
1936
2.34 IPS |
|
Pose Estimation (F16)
|
100% |
6826
8.27 IPS |
|
Pose Estimation (I8)
|
100% |
1239
1.50 IPS |
|
Object Detection (F32)
|
100% |
589
44.0 IPS |
|
Object Detection (F16)
|
100% |
935
69.8 IPS |
|
Object Detection (I8)
|
0% |
2673
199.6 IPS |
|
Face Detection (F32)
|
100% |
1580
18.8 IPS |
|
Face Detection (F16)
|
97% |
2702
32.1 IPS |
|
Face Detection (I8)
|
86% |
793
9.43 IPS |
|
Depth Estimation (F32)
|
100% |
484
3.76 IPS |
|
Depth Estimation (F16)
|
100% |
538
4.17 IPS |
|
Depth Estimation (I8)
|
74% |
8190
63.5 IPS |
|
Style Transfer (F32)
|
100% |
1711
2.25 IPS |
|
Style Transfer (F16)
|
100% |
2060
2.71 IPS |
|
Style Transfer (I8)
|
19% |
539
0.71 IPS |
|
Image Super-Resolution (F32)
|
100% |
1029
36.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
3309
118.2 IPS |
|
Image Super-Resolution (I8)
|
98% |
268
9.58 IPS |
|
Text Classification (F32)
|
100% |
4
5.26 IPS |
|
Text Classification (F16)
|
100% |
88
126.6 IPS |
|
Text Classification (I8)
|
94% |
30
43.4 IPS |
|
Machine Translation (F32)
|
100% |
238
4.38 IPS |
|
Machine Translation (F16)
|
100% |
250
4.59 IPS |
|
Machine Translation (I8)
|
64% |
297
5.47 IPS |