Upload Date | January 19 2022 09:01 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-G970N |
Model ID | samsung SM-G970N |
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% |
603
64.6 IPS |
|
Image Classification (F16)
|
100% |
861
92.2 IPS |
|
Image Classification (I8)
|
80% |
727
77.9 IPS |
|
Image Segmentation (F32)
|
100% |
1703
10.5 IPS |
|
Image Segmentation (F16)
|
100% |
3045
18.8 IPS |
|
Image Segmentation (I8)
|
89% |
3421
21.1 IPS |
|
Pose Estimation (F32)
|
100% |
432
1.75 IPS |
|
Pose Estimation (F16)
|
100% |
1969
7.97 IPS |
|
Pose Estimation (I8)
|
80% |
1866
7.55 IPS |
|
Object Detection (F32)
|
100% |
369
12.9 IPS |
|
Object Detection (F16)
|
100% |
552
19.4 IPS |
|
Object Detection (I8)
|
54% |
504
17.7 IPS |
|
Face Detection (F32)
|
100% |
1261
14.5 IPS |
|
Face Detection (F16)
|
97% |
2065
23.7 IPS |
|
Face Detection (I8)
|
75% |
1668
19.2 IPS |
|
Text Classification (F32)
|
100% |
496
196.0 IPS |
|
Text Classification (F16)
|
98% |
611
241.7 IPS |
|
Machine Translation (F32)
|
100% |
544
83.8 IPS |
|
Machine Translation (F16)
|
100% |
534
82.3 IPS |