Upload Date | July 04 2024 07:46 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 13 |
Model ID | Xiaomi 2211133C |
Motherboard | kalama |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 3 Cores @ 2.02 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Cluster 3 | 1 Core @ 3.19 GHz |
Memory Information | |
---|---|
Size | 7.04 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
530
99.2 IPS |
|
Image Classification (F16)
|
100% |
535
100.0 IPS |
|
Image Classification (I8)
|
97% |
894
167.3 IPS |
|
Image Segmentation (F32)
|
100% |
700
11.7 IPS |
|
Image Segmentation (F16)
|
100% |
697
11.6 IPS |
|
Image Segmentation (I8)
|
98% |
778
13.0 IPS |
|
Pose Estimation (F32)
|
100% |
1254
1.52 IPS |
|
Pose Estimation (F16)
|
100% |
1249
1.51 IPS |
|
Pose Estimation (I8)
|
100% |
5224
6.33 IPS |
|
Object Detection (F32)
|
100% |
552
41.2 IPS |
|
Object Detection (F16)
|
100% |
559
41.7 IPS |
|
Object Detection (I8)
|
61% |
1172
87.5 IPS |
|
Face Detection (F32)
|
100% |
1139
13.5 IPS |
|
Face Detection (F16)
|
100% |
1177
14.0 IPS |
|
Face Detection (I8)
|
86% |
1987
23.6 IPS |
|
Depth Estimation (F32)
|
100% |
1277
9.90 IPS |
|
Depth Estimation (F16)
|
100% |
1268
9.84 IPS |
|
Depth Estimation (I8)
|
95% |
2338
18.1 IPS |
|
Style Transfer (F32)
|
100% |
2360
3.10 IPS |
|
Style Transfer (F16)
|
100% |
2338
3.08 IPS |
|
Style Transfer (I8)
|
98% |
4934
6.49 IPS |
|
Image Super-Resolution (F32)
|
100% |
843
30.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
892
31.9 IPS |
|
Image Super-Resolution (I8)
|
98% |
2218
79.2 IPS |
|
Text Classification (F32)
|
100% |
611
878.3 IPS |
|
Text Classification (F16)
|
100% |
618
888.0 IPS |
|
Text Classification (I8)
|
92% |
453
651.6 IPS |
|
Machine Translation (F32)
|
100% |
1295
23.8 IPS |
|
Machine Translation (F16)
|
100% |
1294
23.8 IPS |
|
Machine Translation (I8)
|
64% |
427
7.86 IPS |