Upload Date | April 14 2022 05:12 PM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-S908B |
Model ID | samsung SM-S908B |
Motherboard | s5e9925 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.82 GHz |
Cluster 1 | 4 Cores @ 1.82 GHz |
Cluster 2 | 3 Cores @ 2.52 GHz |
Cluster 3 | 1 Core @ 2.80 GHz |
Memory Information | |
---|---|
Size | 10.27 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
195
20.9 IPS |
|
Image Classification (F16)
|
100% |
103
11.1 IPS |
|
Image Classification (I8)
|
81% |
450
48.3 IPS |
|
Image Segmentation (F32)
|
100% |
606
3.74 IPS |
|
Image Segmentation (F16)
|
100% |
583
3.60 IPS |
|
Image Segmentation (I8)
|
89% |
813
5.02 IPS |
|
Pose Estimation (F32)
|
100% |
290
1.17 IPS |
|
Pose Estimation (F16)
|
100% |
294
1.19 IPS |
|
Pose Estimation (I8)
|
80% |
139
0.56 IPS |
|
Object Detection (F32)
|
100% |
192
6.74 IPS |
|
Object Detection (F16)
|
100% |
186
6.52 IPS |
|
Object Detection (I8)
|
52% |
500
17.5 IPS |
|
Face Detection (F32)
|
100% |
380
4.37 IPS |
|
Face Detection (F16)
|
100% |
394
4.52 IPS |
|
Face Detection (I8)
|
75% |
607
6.98 IPS |
|
Text Classification (F32)
|
100% |
1131
447.4 IPS |
|
Text Classification (F16)
|
100% |
1135
448.8 IPS |
|
Machine Translation (F32)
|
100% |
973
150.0 IPS |
|
Machine Translation (F16)
|
100% |
976
150.4 IPS |