Upload Date | September 03 2024 03:59 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
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 | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
461
49.4 IPS |
|
Image Classification (F16)
|
100% |
810
86.7 IPS |
|
Image Classification (I8)
|
80% |
944
101.1 IPS |
|
Image Segmentation (F32)
|
100% |
1371
8.47 IPS |
|
Image Segmentation (F16)
|
100% |
2377
14.7 IPS |
|
Image Segmentation (I8)
|
89% |
2293
14.2 IPS |
|
Pose Estimation (F32)
|
100% |
1147
4.64 IPS |
|
Pose Estimation (F16)
|
100% |
3066
12.4 IPS |
|
Pose Estimation (I8)
|
80% |
2963
12.0 IPS |
|
Object Detection (F32)
|
100% |
550
19.3 IPS |
|
Object Detection (F16)
|
100% |
838
29.4 IPS |
|
Object Detection (I8)
|
54% |
782
27.5 IPS |
|
Face Detection (F32)
|
100% |
1776
20.4 IPS |
|
Face Detection (F16)
|
97% |
3256
37.4 IPS |
|
Face Detection (I8)
|
75% |
2677
30.8 IPS |
|
Text Classification (F32)
|
100% |
1212
479.3 IPS |
|
Text Classification (F16)
|
98% |
1657
655.5 IPS |
|
Machine Translation (F32)
|
100% |
850
131.0 IPS |
|
Machine Translation (F16)
|
100% |
891
137.4 IPS |