Upload Date | February 27 2022 08:38 PM |
Views | 5 |
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 | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
320
34.3 IPS |
|
Image Classification (F16)
|
100% |
835
89.5 IPS |
|
Image Classification (I8)
|
80% |
735
78.7 IPS |
|
Image Segmentation (F32)
|
100% |
1262
7.80 IPS |
|
Image Segmentation (F16)
|
100% |
3091
19.1 IPS |
|
Image Segmentation (I8)
|
89% |
2901
17.9 IPS |
|
Pose Estimation (F32)
|
100% |
480
1.94 IPS |
|
Pose Estimation (F16)
|
100% |
1131
4.58 IPS |
|
Pose Estimation (I8)
|
80% |
1096
4.43 IPS |
|
Object Detection (F32)
|
100% |
247
8.68 IPS |
|
Object Detection (F16)
|
100% |
564
19.8 IPS |
|
Object Detection (I8)
|
54% |
545
19.1 IPS |
|
Face Detection (F32)
|
100% |
1242
14.3 IPS |
|
Face Detection (F16)
|
97% |
2692
30.9 IPS |
|
Face Detection (I8)
|
76% |
2374
27.3 IPS |
|
Text Classification (F32)
|
100% |
314
124.3 IPS |
|
Text Classification (F16)
|
98% |
583
230.5 IPS |
|
Machine Translation (F32)
|
100% |
991
152.8 IPS |
|
Machine Translation (F16)
|
100% |
998
153.9 IPS |