Upload Date | October 24 2022 02:00 PM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 13 |
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% |
324
34.7 IPS |
|
Image Classification (F16)
|
100% |
320
34.2 IPS |
|
Image Classification (I8)
|
81% |
435
46.6 IPS |
|
Image Segmentation (F32)
|
100% |
575
3.55 IPS |
|
Image Segmentation (F16)
|
100% |
556
3.43 IPS |
|
Image Segmentation (I8)
|
89% |
785
4.85 IPS |
|
Pose Estimation (F32)
|
100% |
289
1.17 IPS |
|
Pose Estimation (F16)
|
100% |
276
1.12 IPS |
|
Pose Estimation (I8)
|
80% |
131
0.53 IPS |
|
Object Detection (F32)
|
100% |
274
9.61 IPS |
|
Object Detection (F16)
|
100% |
353
12.4 IPS |
|
Object Detection (I8)
|
52% |
484
17.0 IPS |
|
Face Detection (F32)
|
100% |
486
5.59 IPS |
|
Face Detection (F16)
|
100% |
462
5.31 IPS |
|
Face Detection (I8)
|
75% |
588
6.76 IPS |
|
Text Classification (F32)
|
100% |
1066
421.5 IPS |
|
Text Classification (F16)
|
100% |
1116
441.5 IPS |
|
Machine Translation (F32)
|
100% |
924
142.4 IPS |
|
Machine Translation (F16)
|
100% |
950
146.4 IPS |