Upload Date | February 27 2022 01:29 AM |
Views | 4 |
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 | 7.13 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
228
24.5 IPS |
|
Image Classification (F16)
|
100% |
228
24.5 IPS |
|
Image Classification (I8)
|
81% |
147
15.8 IPS |
|
Image Segmentation (F32)
|
100% |
493
3.05 IPS |
|
Image Segmentation (F16)
|
100% |
475
2.93 IPS |
|
Image Segmentation (I8)
|
89% |
683
4.22 IPS |
|
Pose Estimation (F32)
|
100% |
245
0.99 IPS |
|
Pose Estimation (F16)
|
100% |
246
0.99 IPS |
|
Pose Estimation (I8)
|
80% |
187
0.76 IPS |
|
Object Detection (F32)
|
100% |
310
10.9 IPS |
|
Object Detection (F16)
|
100% |
296
10.4 IPS |
|
Object Detection (I8)
|
52% |
225
7.89 IPS |
|
Face Detection (F32)
|
100% |
501
5.76 IPS |
|
Face Detection (F16)
|
100% |
474
5.45 IPS |
|
Face Detection (I8)
|
75% |
390
4.48 IPS |
|
Text Classification (F32)
|
100% |
382
151.2 IPS |
|
Text Classification (F16)
|
100% |
359
142.0 IPS |
|
Machine Translation (F32)
|
100% |
719
110.8 IPS |
|
Machine Translation (F16)
|
100% |
715
110.2 IPS |