Upload Date | July 18 2024 04:04 PM |
Views | 3 |
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 | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
280
52.4 IPS |
|
Image Classification (F16)
|
100% |
278
52.0 IPS |
|
Image Classification (I8)
|
97% |
611
114.3 IPS |
|
Image Segmentation (F32)
|
100% |
385
6.43 IPS |
|
Image Segmentation (F16)
|
100% |
378
6.32 IPS |
|
Image Segmentation (I8)
|
98% |
486
8.12 IPS |
|
Pose Estimation (F32)
|
100% |
665
0.81 IPS |
|
Pose Estimation (F16)
|
100% |
610
0.74 IPS |
|
Pose Estimation (I8)
|
100% |
2801
3.39 IPS |
|
Object Detection (F32)
|
100% |
292
21.8 IPS |
|
Object Detection (F16)
|
100% |
293
21.8 IPS |
|
Object Detection (I8)
|
61% |
792
59.1 IPS |
|
Face Detection (F32)
|
100% |
639
7.60 IPS |
|
Face Detection (F16)
|
100% |
638
7.59 IPS |
|
Face Detection (I8)
|
86% |
1529
18.2 IPS |
|
Depth Estimation (F32)
|
100% |
676
5.24 IPS |
|
Depth Estimation (F16)
|
100% |
648
5.02 IPS |
|
Depth Estimation (I8)
|
95% |
1376
10.7 IPS |
|
Style Transfer (F32)
|
100% |
1176
1.55 IPS |
|
Style Transfer (F16)
|
100% |
1118
1.47 IPS |
|
Style Transfer (I8)
|
98% |
2050
2.70 IPS |
|
Image Super-Resolution (F32)
|
100% |
380
13.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
378
13.5 IPS |
|
Image Super-Resolution (I8)
|
98% |
1255
44.8 IPS |
|
Text Classification (F32)
|
100% |
343
492.9 IPS |
|
Text Classification (F16)
|
100% |
334
480.5 IPS |
|
Text Classification (I8)
|
92% |
285
409.6 IPS |
|
Machine Translation (F32)
|
100% |
686
12.6 IPS |
|
Machine Translation (F16)
|
100% |
646
11.9 IPS |
|
Machine Translation (I8)
|
64% |
242
4.45 IPS |