Upload Date | December 26 2024 06:23 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm Snapdragon 855 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy A90 5G |
Model ID | samsung SM-A908N |
Motherboard | msmnile |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 5.25 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
141
26.2 IPS |
|
Image Classification (HP)
|
100% |
143
26.6 IPS |
|
Image Classification (Q)
|
99% |
339
63.3 IPS |
|
Image Segmentation (SP)
|
100% |
191
3.10 IPS |
|
Image Segmentation (HP)
|
100% |
193
3.12 IPS |
|
Image Segmentation (Q)
|
98% |
346
5.63 IPS |
|
Pose Estimation (SP)
|
100% |
255
0.30 IPS |
|
Pose Estimation (HP)
|
100% |
252
0.29 IPS |
|
Pose Estimation (Q)
|
98% |
966
1.13 IPS |
|
Object Detection (SP)
|
100% |
142
11.2 IPS |
|
Object Detection (HP)
|
100% |
142
11.2 IPS |
|
Object Detection (Q)
|
87% |
383
30.7 IPS |
|
Face Detection (SP)
|
100% |
354
4.21 IPS |
|
Face Detection (HP)
|
100% |
358
4.25 IPS |
|
Face Detection (Q)
|
97% |
713
8.50 IPS |
|
Depth Estimation (SP)
|
100% |
300
2.31 IPS |
|
Depth Estimation (HP)
|
99% |
301
2.32 IPS |
|
Depth Estimation (Q)
|
64% |
696
6.31 IPS |
|
Style Transfer (SP)
|
100% |
490
0.63 IPS |
|
Style Transfer (HP)
|
100% |
493
0.63 IPS |
|
Style Transfer (Q)
|
98% |
1492
1.92 IPS |
|
Image Super-Resolution (SP)
|
100% |
146
5.40 IPS |
|
Image Super-Resolution (HP)
|
100% |
146
5.37 IPS |
|
Image Super-Resolution (Q)
|
97% |
522
19.3 IPS |
|
Text Classification (SP)
|
100% |
215
286.7 IPS |
|
Text Classification (HP)
|
100% |
218
290.8 IPS |
|
Text Classification (Q)
|
91% |
340
457.1 IPS |
|
Machine Translation (SP)
|
100% |
354
6.09 IPS |
|
Machine Translation (HP)
|
100% |
362
6.23 IPS |
|
Machine Translation (Q)
|
57% |
277
6.77 IPS |