User | andreadandrea |
Upload Date | January 04 2025 12:43 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
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% |
100
18.6 IPS |
|
Image Classification (HP)
|
100% |
101
18.7 IPS |
|
Image Classification (Q)
|
99% |
7292
1.36 KIPS |
|
Image Segmentation (SP)
|
100% |
134
2.18 IPS |
|
Image Segmentation (HP)
|
100% |
136
2.20 IPS |
|
Image Segmentation (Q)
|
98% |
4880
79.4 IPS |
|
Pose Estimation (SP)
|
100% |
183
0.21 IPS |
|
Pose Estimation (HP)
|
100% |
183
0.21 IPS |
|
Pose Estimation (Q)
|
94% |
44223
51.8 IPS |
|
Object Detection (SP)
|
100% |
99
7.89 IPS |
|
Object Detection (HP)
|
100% |
100
7.91 IPS |
|
Object Detection (Q)
|
88% |
3040
243.5 IPS |
|
Face Detection (SP)
|
100% |
259
3.08 IPS |
|
Face Detection (HP)
|
100% |
261
3.11 IPS |
|
Face Detection (Q)
|
97% |
18464
220.2 IPS |
|
Depth Estimation (SP)
|
100% |
223
1.72 IPS |
|
Depth Estimation (HP)
|
99% |
223
1.72 IPS |
|
Depth Estimation (Q)
|
64% |
18658
171.8 IPS |
|
Style Transfer (SP)
|
100% |
391
0.50 IPS |
|
Style Transfer (HP)
|
100% |
391
0.50 IPS |
|
Style Transfer (Q)
|
98% |
89561
115.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
112
4.12 IPS |
|
Image Super-Resolution (HP)
|
100% |
112
4.13 IPS |
|
Image Super-Resolution (Q)
|
97% |
20907
774.7 IPS |
|
Text Classification (SP)
|
100% |
151
201.5 IPS |
|
Text Classification (HP)
|
100% |
151
201.8 IPS |
|
Text Classification (Q)
|
94% |
2257
3.03 KIPS |
|
Machine Translation (SP)
|
100% |
246
4.24 IPS |
|
Machine Translation (HP)
|
100% |
245
4.22 IPS |
|
Machine Translation (Q)
|
50% |
364
12.6 IPS |