Upload Date | November 10 2024 01:29 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi K50 Pro |
Model ID | Xiaomi 22011211C |
Motherboard | matisse |
Governor | sugov_ext |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.60 GHz |
Cluster 1 | 4 Cores @ 1.60 GHz |
Cluster 2 | 3 Cores @ 2.85 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 11.19 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
384
71.8 IPS |
|
Image Classification (F16)
|
100% |
493
92.3 IPS |
|
Image Classification (I8)
|
97% |
405
75.7 IPS |
|
Image Segmentation (F32)
|
100% |
413
6.90 IPS |
|
Image Segmentation (F16)
|
100% |
312
5.21 IPS |
|
Image Segmentation (I8)
|
98% |
371
6.20 IPS |
|
Pose Estimation (F32)
|
100% |
553
0.67 IPS |
|
Pose Estimation (F16)
|
100% |
789
0.96 IPS |
|
Pose Estimation (I8)
|
100% |
788
0.95 IPS |
|
Object Detection (F32)
|
100% |
230
17.2 IPS |
|
Object Detection (F16)
|
100% |
221
16.5 IPS |
|
Object Detection (I8)
|
62% |
228
17.0 IPS |
|
Face Detection (F32)
|
100% |
1382
16.4 IPS |
|
Face Detection (F16)
|
98% |
1367
16.3 IPS |
|
Face Detection (I8)
|
86% |
1545
18.4 IPS |
|
Depth Estimation (F32)
|
100% |
812
6.29 IPS |
|
Depth Estimation (F16)
|
100% |
996
7.73 IPS |
|
Depth Estimation (I8)
|
95% |
1006
7.80 IPS |
|
Style Transfer (F32)
|
100% |
2143
2.82 IPS |
|
Style Transfer (F16)
|
100% |
3093
4.07 IPS |
|
Style Transfer (I8)
|
98% |
3110
4.09 IPS |
|
Image Super-Resolution (F32)
|
100% |
440
15.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
626
22.4 IPS |
|
Image Super-Resolution (I8)
|
98% |
591
21.1 IPS |
|
Text Classification (F32)
|
100% |
234
335.7 IPS |
|
Text Classification (F16)
|
100% |
237
340.9 IPS |
|
Text Classification (I8)
|
92% |
480
690.4 IPS |
|
Machine Translation (F32)
|
100% |
363
6.67 IPS |
|
Machine Translation (F16)
|
100% |
369
6.78 IPS |
|
Machine Translation (I8)
|
64% |
450
8.29 IPS |