Upload Date | August 17 2024 12:08 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 10 |
Model | samsung SM-N960N |
Model ID | samsung SM-N960N |
Motherboard | exynos9810 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 2 revision 0 |
Base Frequency | 1.79 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 4 Cores @ 2.70 GHz |
Memory Information | |
---|---|
Size | 5.48 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
610
65.4 IPS |
|
Image Classification (F16)
|
100% |
981
105.2 IPS |
|
Image Classification (I8)
|
81% |
958
102.6 IPS |
|
Image Segmentation (F32)
|
100% |
1323
8.17 IPS |
|
Image Segmentation (F16)
|
100% |
2939
18.2 IPS |
|
Image Segmentation (I8)
|
89% |
2815
17.4 IPS |
|
Pose Estimation (F32)
|
100% |
289
1.17 IPS |
|
Pose Estimation (F16)
|
0% |
1040
4.21 IPS |
|
Pose Estimation (I8)
|
0% |
1037
4.20 IPS |
|
Object Detection (F32)
|
100% |
486
17.1 IPS |
|
Object Detection (F16)
|
99% |
932
32.7 IPS |
|
Object Detection (I8)
|
54% |
880
30.9 IPS |
|
Face Detection (F32)
|
100% |
1207
13.9 IPS |
|
Face Detection (F16)
|
97% |
2364
27.2 IPS |
|
Face Detection (I8)
|
75% |
1984
22.8 IPS |
|
Text Classification (F32)
|
100% |
580
229.4 IPS |
|
Text Classification (F16)
|
98% |
907
358.5 IPS |
|
Machine Translation (F32)
|
100% |
423
65.2 IPS |
|
Machine Translation (F16)
|
100% |
432
66.6 IPS |