Upload Date | October 15 2022 02:08 PM |
Views | 1 |
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% |
336
36.0 IPS |
|
Image Classification (F16)
|
100% |
333
35.7 IPS |
|
Image Classification (I8)
|
81% |
174
18.6 IPS |
|
Image Segmentation (F32)
|
100% |
588
3.63 IPS |
|
Image Segmentation (F16)
|
100% |
592
3.66 IPS |
|
Image Segmentation (I8)
|
89% |
755
4.66 IPS |
|
Pose Estimation (F32)
|
100% |
295
1.19 IPS |
|
Pose Estimation (F16)
|
100% |
287
1.16 IPS |
|
Pose Estimation (I8)
|
80% |
239
0.97 IPS |
|
Object Detection (F32)
|
100% |
401
14.1 IPS |
|
Object Detection (F16)
|
100% |
411
14.4 IPS |
|
Object Detection (I8)
|
52% |
266
9.32 IPS |
|
Face Detection (F32)
|
100% |
633
7.28 IPS |
|
Face Detection (F16)
|
100% |
629
7.23 IPS |
|
Face Detection (I8)
|
75% |
477
5.49 IPS |
|
Text Classification (F32)
|
100% |
363
143.5 IPS |
|
Text Classification (F16)
|
100% |
287
113.5 IPS |
|
Machine Translation (F32)
|
100% |
970
149.5 IPS |
|
Machine Translation (F16)
|
100% |
968
149.3 IPS |