Upload Date | March 31 2022 06:08 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% |
171
18.3 IPS |
|
Image Classification (F16)
|
100% |
93
10.0 IPS |
|
Image Classification (I8)
|
81% |
247
26.5 IPS |
|
Image Segmentation (F32)
|
100% |
397
2.45 IPS |
|
Image Segmentation (F16)
|
100% |
383
2.36 IPS |
|
Image Segmentation (I8)
|
89% |
445
2.75 IPS |
|
Pose Estimation (F32)
|
100% |
172
0.70 IPS |
|
Pose Estimation (F16)
|
100% |
192
0.78 IPS |
|
Pose Estimation (I8)
|
80% |
80
0.32 IPS |
|
Object Detection (F32)
|
100% |
159
5.59 IPS |
|
Object Detection (F16)
|
100% |
151
5.31 IPS |
|
Object Detection (I8)
|
52% |
276
9.69 IPS |
|
Face Detection (F32)
|
100% |
262
3.01 IPS |
|
Face Detection (F16)
|
100% |
298
3.42 IPS |
|
Face Detection (I8)
|
75% |
339
3.89 IPS |
|
Text Classification (F32)
|
100% |
637
251.8 IPS |
|
Text Classification (F16)
|
100% |
637
251.9 IPS |
|
Machine Translation (F32)
|
100% |
569
87.6 IPS |
|
Machine Translation (F16)
|
100% |
569
87.7 IPS |