User | PeterFan |
Upload Date | July 10 2025 02:52 AM |
Views | 9 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 888 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S21 Ultra 5G |
Model ID | samsung SM-G9980 |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM SM8350 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 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 | 13.96 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
251
46.6 IPS |
|
Image Classification (HP)
|
100% |
241
44.9 IPS |
|
Image Classification (Q)
|
100% |
702
130.5 IPS |
|
Image Segmentation (SP)
|
100% |
329
5.34 IPS |
|
Image Segmentation (HP)
|
100% |
332
5.38 IPS |
|
Image Segmentation (Q)
|
98% |
824
13.4 IPS |
|
Pose Estimation (SP)
|
100% |
1301
1.52 IPS |
|
Pose Estimation (HP)
|
100% |
1295
1.51 IPS |
|
Pose Estimation (Q)
|
84% |
1697
2.01 IPS |
|
Object Detection (SP)
|
100% |
259
20.5 IPS |
|
Object Detection (HP)
|
100% |
258
20.5 IPS |
|
Object Detection (Q)
|
83% |
680
54.9 IPS |
|
Face Detection (SP)
|
100% |
864
10.3 IPS |
|
Face Detection (HP)
|
100% |
867
10.3 IPS |
|
Face Detection (Q)
|
95% |
1694
20.2 IPS |
|
Depth Estimation (SP)
|
100% |
1173
9.04 IPS |
|
Depth Estimation (HP)
|
99% |
1173
9.03 IPS |
|
Depth Estimation (Q)
|
64% |
1033
9.46 IPS |
|
Style Transfer (SP)
|
89% |
1084
1.41 IPS |
|
Style Transfer (HP)
|
89% |
1084
1.41 IPS |
|
Style Transfer (Q)
|
98% |
2472
3.19 IPS |
|
Image Super-Resolution (SP)
|
100% |
290
10.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
290
10.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
628
23.3 IPS |
|
Text Classification (SP)
|
100% |
164
219.3 IPS |
|
Text Classification (HP)
|
100% |
165
219.6 IPS |
|
Text Classification (Q)
|
88% |
262
353.6 IPS |
|
Machine Translation (SP)
|
100% |
249
4.30 IPS |
|
Machine Translation (HP)
|
100% |
246
4.24 IPS |
|
Machine Translation (Q)
|
50% |
152
5.39 IPS |