Upload Date | November 11 2024 01:15 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 865 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy S20 5G |
Model ID | samsung SM-G981U |
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 | 10.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
439
81.7 IPS |
|
Image Classification (HP)
|
100% |
507
94.3 IPS |
|
Image Classification (Q)
|
100% |
1424
264.8 IPS |
|
Image Segmentation (SP)
|
100% |
646
10.5 IPS |
|
Image Segmentation (HP)
|
100% |
620
10.0 IPS |
|
Image Segmentation (Q)
|
98% |
1688
27.4 IPS |
|
Pose Estimation (SP)
|
100% |
2145
2.50 IPS |
|
Pose Estimation (HP)
|
100% |
2021
2.36 IPS |
|
Pose Estimation (Q)
|
84% |
3412
4.05 IPS |
|
Object Detection (SP)
|
100% |
452
35.9 IPS |
|
Object Detection (HP)
|
100% |
456
36.2 IPS |
|
Object Detection (Q)
|
83% |
1390
112.3 IPS |
|
Face Detection (SP)
|
100% |
1475
17.5 IPS |
|
Face Detection (HP)
|
100% |
1488
17.7 IPS |
|
Face Detection (Q)
|
95% |
3299
39.4 IPS |
|
Depth Estimation (SP)
|
100% |
1849
14.2 IPS |
|
Depth Estimation (HP)
|
99% |
1703
13.1 IPS |
|
Depth Estimation (Q)
|
64% |
3067
28.1 IPS |
|
Style Transfer (SP)
|
89% |
3540
4.60 IPS |
|
Style Transfer (HP)
|
89% |
3676
4.77 IPS |
|
Style Transfer (Q)
|
98% |
7795
10.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
289
10.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
295
10.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
635
23.5 IPS |
|
Text Classification (SP)
|
100% |
167
222.4 IPS |
|
Text Classification (HP)
|
100% |
166
222.1 IPS |
|
Text Classification (Q)
|
88% |
265
357.6 IPS |
|
Machine Translation (SP)
|
100% |
246
4.23 IPS |
|
Machine Translation (HP)
|
100% |
242
4.16 IPS |
|
Machine Translation (Q)
|
50% |
155
5.50 IPS |