Upload Date | December 25 2024 09:26 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 778G |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy A52S 5G |
Model ID | samsung SM-A528B |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.25 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
150
27.9 IPS |
|
Image Classification (HP)
|
100% |
147
27.4 IPS |
|
Image Classification (Q)
|
100% |
514
95.6 IPS |
|
Image Segmentation (SP)
|
100% |
266
4.32 IPS |
|
Image Segmentation (HP)
|
100% |
166
2.69 IPS |
|
Image Segmentation (Q)
|
98% |
669
10.9 IPS |
|
Pose Estimation (SP)
|
100% |
1088
1.27 IPS |
|
Pose Estimation (HP)
|
100% |
662
0.77 IPS |
|
Pose Estimation (Q)
|
84% |
1098
1.30 IPS |
|
Object Detection (SP)
|
100% |
198
15.7 IPS |
|
Object Detection (HP)
|
100% |
150
11.9 IPS |
|
Object Detection (Q)
|
83% |
531
42.9 IPS |
|
Face Detection (SP)
|
100% |
677
8.05 IPS |
|
Face Detection (HP)
|
100% |
364
4.33 IPS |
|
Face Detection (Q)
|
95% |
1373
16.4 IPS |
|
Depth Estimation (SP)
|
100% |
517
3.98 IPS |
|
Depth Estimation (HP)
|
99% |
497
3.83 IPS |
|
Depth Estimation (Q)
|
64% |
1348
12.3 IPS |
|
Style Transfer (SP)
|
89% |
1164
1.51 IPS |
|
Style Transfer (HP)
|
89% |
1146
1.49 IPS |
|
Style Transfer (Q)
|
98% |
3499
4.51 IPS |
|
Image Super-Resolution (SP)
|
100% |
287
10.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
290
10.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
621
23.0 IPS |
|
Text Classification (SP)
|
100% |
181
241.4 IPS |
|
Text Classification (HP)
|
100% |
180
240.3 IPS |
|
Text Classification (Q)
|
88% |
341
459.8 IPS |
|
Machine Translation (SP)
|
100% |
334
5.75 IPS |
|
Machine Translation (HP)
|
100% |
340
5.85 IPS |
|
Machine Translation (Q)
|
50% |
261
9.27 IPS |