Upload Date | September 17 2024 11:49 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 865+ |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy Note20 Ultra 5G |
Model ID | samsung SM-N986N |
Motherboard | kona |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 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 @ 3.09 GHz |
Memory Information | |
---|---|
Size | 10.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
519
96.4 IPS |
|
Image Classification (HP)
|
100% |
538
100.1 IPS |
|
Image Classification (Q)
|
100% |
1464
272.2 IPS |
|
Image Segmentation (SP)
|
100% |
665
10.8 IPS |
|
Image Segmentation (HP)
|
100% |
666
10.8 IPS |
|
Image Segmentation (Q)
|
98% |
1704
27.7 IPS |
|
Pose Estimation (SP)
|
100% |
2184
2.55 IPS |
|
Pose Estimation (HP)
|
100% |
2163
2.52 IPS |
|
Pose Estimation (Q)
|
84% |
3613
4.29 IPS |
|
Object Detection (SP)
|
100% |
479
38.0 IPS |
|
Object Detection (HP)
|
100% |
486
38.5 IPS |
|
Object Detection (Q)
|
83% |
1430
115.5 IPS |
|
Face Detection (SP)
|
100% |
1599
19.0 IPS |
|
Face Detection (HP)
|
100% |
1561
18.5 IPS |
|
Face Detection (Q)
|
95% |
3429
40.9 IPS |
|
Depth Estimation (SP)
|
100% |
1811
14.0 IPS |
|
Depth Estimation (HP)
|
99% |
1979
15.3 IPS |
|
Depth Estimation (Q)
|
64% |
3369
30.9 IPS |
|
Style Transfer (SP)
|
89% |
3760
4.88 IPS |
|
Style Transfer (HP)
|
89% |
3774
4.90 IPS |
|
Style Transfer (Q)
|
98% |
7231
9.32 IPS |
|
Image Super-Resolution (SP)
|
100% |
1087
40.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
1124
41.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
2014
74.6 IPS |
|
Text Classification (SP)
|
100% |
159
212.6 IPS |
|
Text Classification (HP)
|
100% |
157
210.0 IPS |
|
Text Classification (Q)
|
88% |
254
343.1 IPS |
|
Machine Translation (SP)
|
100% |
245
4.22 IPS |
|
Machine Translation (HP)
|
100% |
240
4.13 IPS |
|
Machine Translation (Q)
|
50% |
150
5.31 IPS |