User | aguijon |
Upload Date | August 28 2024 04:39 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 11 |
Model | samsung SM-G970F |
Model ID | samsung SM-G970F |
Motherboard | exynos9820 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 3 revision 0 |
Base Frequency | 1.95 GHz |
Cluster 1 | 4 Cores @ 1.95 GHz |
Cluster 2 | 2 Cores @ 2.31 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 5.29 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
436
46.7 IPS |
|
Image Classification (F16)
|
100% |
698
74.8 IPS |
|
Image Classification (I8)
|
80% |
741
79.4 IPS |
|
Image Segmentation (F32)
|
100% |
1144
7.07 IPS |
|
Image Segmentation (F16)
|
100% |
2131
13.2 IPS |
|
Image Segmentation (I8)
|
89% |
2928
18.1 IPS |
|
Pose Estimation (F32)
|
100% |
414
1.68 IPS |
|
Pose Estimation (F16)
|
100% |
2061
8.34 IPS |
|
Pose Estimation (I8)
|
80% |
2020
8.17 IPS |
|
Object Detection (F32)
|
100% |
586
20.6 IPS |
|
Object Detection (F16)
|
100% |
982
34.5 IPS |
|
Object Detection (I8)
|
54% |
963
33.8 IPS |
|
Face Detection (F32)
|
100% |
1455
16.7 IPS |
|
Face Detection (F16)
|
97% |
2756
31.7 IPS |
|
Face Detection (I8)
|
75% |
2315
26.6 IPS |
|
Text Classification (F32)
|
100% |
605
239.3 IPS |
|
Text Classification (F16)
|
98% |
649
256.6 IPS |
|
Machine Translation (F32)
|
100% |
371
57.1 IPS |
|
Machine Translation (F16)
|
100% |
370
57.0 IPS |