User | Blu4all |
Upload Date | December 19 2024 10:37 PM |
Views | 2 |
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-N986U |
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% |
180
33.5 IPS |
|
Image Classification (HP)
|
100% |
182
33.8 IPS |
|
Image Classification (Q)
|
100% |
481
89.5 IPS |
|
Image Segmentation (SP)
|
100% |
191
3.10 IPS |
|
Image Segmentation (HP)
|
100% |
188
3.05 IPS |
|
Image Segmentation (Q)
|
98% |
498
8.11 IPS |
|
Pose Estimation (SP)
|
100% |
639
0.75 IPS |
|
Pose Estimation (HP)
|
100% |
631
0.74 IPS |
|
Pose Estimation (Q)
|
84% |
1178
1.40 IPS |
|
Object Detection (SP)
|
100% |
169
13.4 IPS |
|
Object Detection (HP)
|
100% |
171
13.6 IPS |
|
Object Detection (Q)
|
83% |
474
38.3 IPS |
|
Face Detection (SP)
|
100% |
374
4.44 IPS |
|
Face Detection (HP)
|
100% |
363
4.32 IPS |
|
Face Detection (Q)
|
95% |
878
10.5 IPS |
|
Depth Estimation (SP)
|
100% |
513
3.95 IPS |
|
Depth Estimation (HP)
|
99% |
524
4.04 IPS |
|
Depth Estimation (Q)
|
64% |
958
8.77 IPS |
|
Style Transfer (SP)
|
89% |
1126
1.46 IPS |
|
Style Transfer (HP)
|
89% |
1136
1.47 IPS |
|
Style Transfer (Q)
|
98% |
2515
3.24 IPS |
|
Image Super-Resolution (SP)
|
100% |
308
11.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
280
10.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
607
22.5 IPS |
|
Text Classification (SP)
|
100% |
163
217.2 IPS |
|
Text Classification (HP)
|
100% |
162
216.4 IPS |
|
Text Classification (Q)
|
88% |
269
362.3 IPS |
|
Machine Translation (SP)
|
100% |
249
4.28 IPS |
|
Machine Translation (HP)
|
100% |
245
4.22 IPS |
|
Machine Translation (Q)
|
50% |
151
5.38 IPS |