Upload Date | May 26 2024 05:36 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy Note10 5G |
Model ID | samsung SM-N971N |
Motherboard | exynos9825 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 3 revision 0 |
Base Frequency | 1.95 GHz |
Cluster 1 | 4 Cores @ 1.95 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 11.02 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
165
30.9 IPS |
|
Image Classification (F16)
|
100% |
161
30.2 IPS |
|
Image Classification (I8)
|
97% |
357
66.8 IPS |
|
Image Segmentation (F32)
|
100% |
220
3.67 IPS |
|
Image Segmentation (F16)
|
100% |
279
4.67 IPS |
|
Image Segmentation (I8)
|
98% |
395
6.60 IPS |
|
Pose Estimation (F32)
|
100% |
1128
1.37 IPS |
|
Pose Estimation (F16)
|
100% |
4563
5.53 IPS |
|
Pose Estimation (I8)
|
100% |
972
1.18 IPS |
|
Object Detection (F32)
|
100% |
169
12.6 IPS |
|
Object Detection (F16)
|
100% |
168
12.5 IPS |
|
Object Detection (I8)
|
61% |
381
28.5 IPS |
|
Face Detection (F32)
|
100% |
406
4.82 IPS |
|
Face Detection (F16)
|
100% |
407
4.84 IPS |
|
Face Detection (I8)
|
86% |
784
9.32 IPS |
|
Depth Estimation (F32)
|
100% |
364
2.82 IPS |
|
Depth Estimation (F16)
|
100% |
363
2.81 IPS |
|
Depth Estimation (I8)
|
95% |
872
6.76 IPS |
|
Style Transfer (F32)
|
100% |
692
0.91 IPS |
|
Style Transfer (F16)
|
33% |
709
0.93 IPS |
|
Style Transfer (I8)
|
29% |
1616
2.13 IPS |
|
Image Super-Resolution (F32)
|
0% |
5207
186.0 IPS |
|
Image Super-Resolution (F16)
|
0% |
4611
164.7 IPS |
|
Image Super-Resolution (I8)
|
98% |
615
22.0 IPS |
|
Text Classification (F32)
|
36% |
38
54.4 IPS |
|
Text Classification (F16)
|
36% |
38
54.4 IPS |
|
Text Classification (I8)
|
78% |
47
67.3 IPS |
|
Machine Translation (F32)
|
100% |
398
7.32 IPS |
|
Machine Translation (F16)
|
100% |
380
6.98 IPS |
|
Machine Translation (I8)
|
64% |
421
7.74 IPS |