Upload Date | January 19 2022 07:02 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-G9900 |
Model ID | samsung SM-G9900 |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM SM8350 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.19 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1041
111.6 IPS |
|
Image Classification (F16)
|
100% |
2121
227.3 IPS |
|
Image Classification (I8)
|
79% |
3112
333.5 IPS |
|
Image Segmentation (F32)
|
100% |
2430
15.0 IPS |
|
Image Segmentation (F16)
|
100% |
4554
28.1 IPS |
|
Image Segmentation (I8)
|
89% |
9324
57.6 IPS |
|
Pose Estimation (F32)
|
100% |
591
2.39 IPS |
|
Pose Estimation (F16)
|
100% |
2122
8.59 IPS |
|
Pose Estimation (I8)
|
80% |
22800
92.3 IPS |
|
Object Detection (F32)
|
100% |
866
30.4 IPS |
|
Object Detection (F16)
|
100% |
1161
40.8 IPS |
|
Object Detection (I8)
|
56% |
1537
53.9 IPS |
|
Face Detection (F32)
|
100% |
1724
19.8 IPS |
|
Face Detection (F16)
|
97% |
2980
34.2 IPS |
|
Face Detection (I8)
|
76% |
18804
216.0 IPS |
|
Text Classification (F32)
|
100% |
13
4.97 IPS |
|
Text Classification (F16)
|
100% |
316
125.1 IPS |
|
Machine Translation (F32)
|
100% |
632
97.4 IPS |
|
Machine Translation (F16)
|
100% |
631
97.3 IPS |