User | monopuerco |
Upload Date | December 24 2024 07:47 PM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 865 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy S20 FE 5G |
Model ID | samsung SM-G781U |
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 @ 2.84 GHz |
Memory Information | |
---|---|
Size | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
194
36.2 IPS |
|
Image Classification (HP)
|
100% |
283
52.6 IPS |
|
Image Classification (Q)
|
97% |
368
68.7 IPS |
|
Image Segmentation (SP)
|
100% |
188
3.04 IPS |
|
Image Segmentation (HP)
|
100% |
247
4.00 IPS |
|
Image Segmentation (Q)
|
98% |
213
3.46 IPS |
|
Pose Estimation (SP)
|
100% |
491
0.57 IPS |
|
Pose Estimation (HP)
|
100% |
989
1.15 IPS |
|
Pose Estimation (Q)
|
95% |
963
1.13 IPS |
|
Object Detection (SP)
|
100% |
201
15.9 IPS |
|
Object Detection (HP)
|
100% |
207
16.4 IPS |
|
Object Detection (Q)
|
89% |
213
17.1 IPS |
|
Face Detection (SP)
|
100% |
615
7.31 IPS |
|
Face Detection (HP)
|
100% |
1188
14.1 IPS |
|
Face Detection (Q)
|
97% |
1156
13.8 IPS |
|
Depth Estimation (SP)
|
100% |
579
4.46 IPS |
|
Depth Estimation (HP)
|
99% |
1118
8.64 IPS |
|
Depth Estimation (Q)
|
62% |
913
8.65 IPS |
|
Style Transfer (SP)
|
100% |
1110
1.43 IPS |
|
Style Transfer (HP)
|
100% |
2842
3.65 IPS |
|
Style Transfer (Q)
|
98% |
2814
3.63 IPS |
|
Image Super-Resolution (SP)
|
100% |
269
9.92 IPS |
|
Image Super-Resolution (HP)
|
100% |
573
21.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
554
20.5 IPS |
|
Text Classification (SP)
|
100% |
52
68.8 IPS |
|
Text Classification (HP)
|
100% |
52
69.2 IPS |
|
Text Classification (Q)
|
91% |
95
127.5 IPS |
|
Machine Translation (SP)
|
100% |
85
1.47 IPS |
|
Machine Translation (HP)
|
100% |
86
1.48 IPS |
|
Machine Translation (Q)
|
57% |
76
1.85 IPS |