User | paultissue |
Upload Date | September 04 2025 12:06 AM |
Views | 13 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 8 Gen 1 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S22 |
Model ID | samsung SM-S901U |
Motherboard | taro |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.50 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 7.05 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
346
64.4 IPS |
|
Image Classification (HP)
|
100% |
585
108.8 IPS |
|
Image Classification (Q)
|
99% |
555
103.6 IPS |
|
Image Segmentation (SP)
|
100% |
653
10.6 IPS |
|
Image Segmentation (HP)
|
100% |
1153
18.7 IPS |
|
Image Segmentation (Q)
|
98% |
1076
17.5 IPS |
|
Pose Estimation (SP)
|
100% |
2395
2.79 IPS |
|
Pose Estimation (HP)
|
99% |
4136
4.83 IPS |
|
Pose Estimation (Q)
|
97% |
4258
4.99 IPS |
|
Object Detection (SP)
|
100% |
261
20.7 IPS |
|
Object Detection (HP)
|
99% |
361
28.6 IPS |
|
Object Detection (Q)
|
85% |
345
27.7 IPS |
|
Face Detection (SP)
|
100% |
1167
13.9 IPS |
|
Face Detection (HP)
|
100% |
2060
24.5 IPS |
|
Face Detection (Q)
|
97% |
1812
21.6 IPS |
|
Depth Estimation (SP)
|
100% |
1174
9.04 IPS |
|
Depth Estimation (HP)
|
98% |
1984
15.3 IPS |
|
Depth Estimation (Q)
|
65% |
1609
14.5 IPS |
|
Style Transfer (SP)
|
100% |
2783
3.58 IPS |
|
Style Transfer (HP)
|
100% |
5918
7.61 IPS |
|
Style Transfer (Q)
|
98% |
5749
7.41 IPS |
|
Image Super-Resolution (SP)
|
100% |
489
18.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
911
33.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1159
42.9 IPS |
|
Text Classification (SP)
|
35% |
22
210.3 IPS |
|
Text Classification (HP)
|
35% |
28
258.6 IPS |
|
Text Classification (Q)
|
35% |
28
251.6 IPS |
|
Machine Translation (SP)
|
100% |
255
4.38 IPS |
|
Machine Translation (HP)
|
97% |
339
5.86 IPS |
|
Machine Translation (Q)
|
64% |
234
4.82 IPS |