Upload Date | September 26 2024 06:14 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
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 | 10.90 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
496
92.8 IPS |
|
Image Classification (F16)
|
100% |
796
149.0 IPS |
|
Image Classification (I8)
|
99% |
547
102.3 IPS |
|
Image Segmentation (F32)
|
100% |
775
12.9 IPS |
|
Image Segmentation (F16)
|
100% |
1201
20.1 IPS |
|
Image Segmentation (I8)
|
98% |
987
16.5 IPS |
|
Pose Estimation (F32)
|
100% |
636
0.77 IPS |
|
Pose Estimation (F16)
|
100% |
922
1.12 IPS |
|
Pose Estimation (I8)
|
100% |
940
1.14 IPS |
|
Object Detection (F32)
|
100% |
332
24.8 IPS |
|
Object Detection (F16)
|
100% |
425
31.8 IPS |
|
Object Detection (I8)
|
62% |
418
31.2 IPS |
|
Face Detection (F32)
|
100% |
1840
21.9 IPS |
|
Face Detection (F16)
|
97% |
2651
31.5 IPS |
|
Face Detection (I8)
|
86% |
2326
27.7 IPS |
|
Depth Estimation (F32)
|
100% |
1106
8.58 IPS |
|
Depth Estimation (F16)
|
100% |
2080
16.1 IPS |
|
Depth Estimation (I8)
|
95% |
2152
16.7 IPS |
|
Style Transfer (F32)
|
100% |
2809
3.69 IPS |
|
Style Transfer (F16)
|
100% |
6465
8.50 IPS |
|
Style Transfer (I8)
|
98% |
6479
8.52 IPS |
|
Image Super-Resolution (F32)
|
100% |
251
8.98 IPS |
|
Image Super-Resolution (F16)
|
100% |
227
8.09 IPS |
|
Image Super-Resolution (I8)
|
98% |
225
8.04 IPS |
|
Text Classification (F32)
|
100% |
313
449.5 IPS |
|
Text Classification (F16)
|
100% |
311
447.6 IPS |
|
Text Classification (I8)
|
92% |
452
649.5 IPS |
|
Machine Translation (F32)
|
100% |
549
10.1 IPS |
|
Machine Translation (F16)
|
100% |
551
10.1 IPS |
|
Machine Translation (I8)
|
64% |
534
9.83 IPS |