Upload Date | June 03 2022 07:24 AM |
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% |
254
27.2 IPS |
|
Image Classification (F16)
|
100% |
246
26.4 IPS |
|
Image Classification (I8)
|
81% |
244
26.1 IPS |
|
Image Segmentation (F32)
|
100% |
408
2.52 IPS |
|
Image Segmentation (F16)
|
100% |
411
2.54 IPS |
|
Image Segmentation (I8)
|
89% |
444
2.74 IPS |
|
Pose Estimation (F32)
|
100% |
189
0.76 IPS |
|
Pose Estimation (F16)
|
100% |
225
0.91 IPS |
|
Pose Estimation (I8)
|
80% |
111
0.45 IPS |
|
Object Detection (F32)
|
100% |
261
9.16 IPS |
|
Object Detection (F16)
|
100% |
293
10.3 IPS |
|
Object Detection (I8)
|
52% |
286
10.1 IPS |
|
Face Detection (F32)
|
100% |
510
5.86 IPS |
|
Face Detection (F16)
|
100% |
542
6.23 IPS |
|
Face Detection (I8)
|
75% |
505
5.80 IPS |
|
Text Classification (F32)
|
100% |
951
376.2 IPS |
|
Text Classification (F16)
|
100% |
949
375.2 IPS |
|
Machine Translation (F32)
|
100% |
898
138.4 IPS |
|
Machine Translation (F16)
|
100% |
899
138.5 IPS |