Upload Date | February 25 2022 02:34 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 | CPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
230
24.6 IPS |
|
Image Classification (F16)
|
100% |
132
14.2 IPS |
|
Image Classification (I8)
|
81% |
200
21.5 IPS |
|
Image Segmentation (F32)
|
100% |
486
3.00 IPS |
|
Image Segmentation (F16)
|
100% |
473
2.92 IPS |
|
Image Segmentation (I8)
|
89% |
702
4.34 IPS |
|
Pose Estimation (F32)
|
100% |
327
1.32 IPS |
|
Pose Estimation (F16)
|
100% |
316
1.28 IPS |
|
Pose Estimation (I8)
|
80% |
242
0.98 IPS |
|
Object Detection (F32)
|
100% |
186
6.51 IPS |
|
Object Detection (F16)
|
100% |
183
6.43 IPS |
|
Object Detection (I8)
|
52% |
222
7.77 IPS |
|
Face Detection (F32)
|
100% |
555
6.38 IPS |
|
Face Detection (F16)
|
100% |
559
6.42 IPS |
|
Face Detection (I8)
|
75% |
399
4.58 IPS |
|
Text Classification (F32)
|
100% |
252
99.5 IPS |
|
Text Classification (F16)
|
100% |
270
106.9 IPS |
|
Machine Translation (F32)
|
100% |
1003
154.6 IPS |
|
Machine Translation (F16)
|
100% |
999
154.0 IPS |