Upload Date | June 27 2022 06:13 PM |
Views | 2 |
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% |
436
46.7 IPS |
|
Image Classification (F16)
|
100% |
443
47.4 IPS |
|
Image Classification (I8)
|
81% |
438
47.0 IPS |
|
Image Segmentation (F32)
|
100% |
669
4.13 IPS |
|
Image Segmentation (F16)
|
100% |
672
4.15 IPS |
|
Image Segmentation (I8)
|
89% |
801
4.95 IPS |
|
Pose Estimation (F32)
|
100% |
287
1.16 IPS |
|
Pose Estimation (F16)
|
100% |
279
1.13 IPS |
|
Pose Estimation (I8)
|
80% |
139
0.56 IPS |
|
Object Detection (F32)
|
100% |
476
16.7 IPS |
|
Object Detection (F16)
|
100% |
478
16.8 IPS |
|
Object Detection (I8)
|
52% |
501
17.6 IPS |
|
Face Detection (F32)
|
100% |
572
6.57 IPS |
|
Face Detection (F16)
|
100% |
567
6.51 IPS |
|
Face Detection (I8)
|
75% |
600
6.90 IPS |
|
Text Classification (F32)
|
100% |
1124
444.6 IPS |
|
Text Classification (F16)
|
100% |
1129
446.4 IPS |
|
Machine Translation (F32)
|
100% |
974
150.1 IPS |
|
Machine Translation (F16)
|
100% |
974
150.1 IPS |