Upload Date | October 15 2022 02:14 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% |
323
34.6 IPS |
|
Image Classification (F16)
|
100% |
331
35.5 IPS |
|
Image Classification (I8)
|
81% |
197
21.1 IPS |
|
Image Segmentation (F32)
|
100% |
696
4.30 IPS |
|
Image Segmentation (F16)
|
100% |
683
4.22 IPS |
|
Image Segmentation (I8)
|
89% |
899
5.56 IPS |
|
Pose Estimation (F32)
|
100% |
274
1.11 IPS |
|
Pose Estimation (F16)
|
100% |
274
1.11 IPS |
|
Pose Estimation (I8)
|
80% |
246
1.00 IPS |
|
Object Detection (F32)
|
100% |
437
15.3 IPS |
|
Object Detection (F16)
|
100% |
421
14.8 IPS |
|
Object Detection (I8)
|
52% |
294
10.3 IPS |
|
Face Detection (F32)
|
100% |
632
7.26 IPS |
|
Face Detection (F16)
|
100% |
615
7.06 IPS |
|
Face Detection (I8)
|
75% |
480
5.51 IPS |
|
Text Classification (F32)
|
100% |
364
143.9 IPS |
|
Text Classification (F16)
|
100% |
402
159.1 IPS |
|
Machine Translation (F32)
|
100% |
765
117.9 IPS |
|
Machine Translation (F16)
|
100% |
710
109.4 IPS |