Upload Date | April 27 2024 04:06 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi Redmi K20 Pro |
Model ID | Xiaomi Redmi K20 Pro |
Motherboard | raphael |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.96 GHz |
Memory Information | |
---|---|
Size | 11.18 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
293
54.8 IPS |
|
Image Classification (F16)
|
100% |
300
56.1 IPS |
|
Image Classification (I8)
|
97% |
609
114.1 IPS |
|
Image Segmentation (F32)
|
100% |
349
5.84 IPS |
|
Image Segmentation (F16)
|
100% |
351
5.86 IPS |
|
Image Segmentation (I8)
|
98% |
411
6.87 IPS |
|
Pose Estimation (F32)
|
100% |
565
0.68 IPS |
|
Pose Estimation (F16)
|
100% |
558
0.68 IPS |
|
Pose Estimation (I8)
|
100% |
2560
3.10 IPS |
|
Object Detection (F32)
|
100% |
310
23.1 IPS |
|
Object Detection (F16)
|
100% |
282
21.1 IPS |
|
Object Detection (I8)
|
61% |
720
53.7 IPS |
|
Face Detection (F32)
|
100% |
602
7.16 IPS |
|
Face Detection (F16)
|
100% |
610
7.25 IPS |
|
Face Detection (I8)
|
86% |
1046
12.4 IPS |
|
Depth Estimation (F32)
|
100% |
558
4.33 IPS |
|
Depth Estimation (F16)
|
100% |
536
4.15 IPS |
|
Depth Estimation (I8)
|
95% |
1108
8.59 IPS |
|
Style Transfer (F32)
|
100% |
832
1.09 IPS |
|
Style Transfer (F16)
|
100% |
833
1.10 IPS |
|
Style Transfer (I8)
|
98% |
1581
2.08 IPS |
|
Image Super-Resolution (F32)
|
100% |
368
13.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
368
13.1 IPS |
|
Image Super-Resolution (I8)
|
98% |
1112
39.7 IPS |
|
Text Classification (F32)
|
100% |
397
570.5 IPS |
|
Text Classification (F16)
|
100% |
344
493.7 IPS |
|
Text Classification (I8)
|
92% |
315
453.1 IPS |
|
Machine Translation (F32)
|
100% |
703
12.9 IPS |
|
Machine Translation (F16)
|
100% |
689
12.7 IPS |
|
Machine Translation (I8)
|
64% |
297
5.47 IPS |