Upload Date | October 13 2025 07:34 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 730 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy A71 |
Model ID | samsung SM-A715F |
Motherboard | sm6150 |
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 | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.34 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
179
33.3 IPS |
|
Image Classification (HP)
|
100% |
261
48.6 IPS |
|
Image Classification (Q)
|
99% |
245
45.6 IPS |
|
Image Segmentation (SP)
|
100% |
257
4.17 IPS |
|
Image Segmentation (HP)
|
100% |
411
6.66 IPS |
|
Image Segmentation (Q)
|
98% |
371
6.04 IPS |
|
Pose Estimation (SP)
|
100% |
987
1.15 IPS |
|
Pose Estimation (HP)
|
99% |
1584
1.85 IPS |
|
Pose Estimation (Q)
|
97% |
1541
1.80 IPS |
|
Object Detection (SP)
|
100% |
128
10.2 IPS |
|
Object Detection (HP)
|
99% |
163
12.9 IPS |
|
Object Detection (Q)
|
85% |
158
12.7 IPS |
|
Face Detection (SP)
|
100% |
582
6.91 IPS |
|
Face Detection (HP)
|
100% |
853
10.1 IPS |
|
Face Detection (Q)
|
97% |
781
9.31 IPS |
|
Depth Estimation (SP)
|
100% |
664
5.11 IPS |
|
Depth Estimation (HP)
|
98% |
1095
8.46 IPS |
|
Depth Estimation (Q)
|
63% |
903
8.34 IPS |
|
Style Transfer (SP)
|
100% |
1606
2.06 IPS |
|
Style Transfer (HP)
|
100% |
2996
3.85 IPS |
|
Style Transfer (Q)
|
98% |
2905
3.75 IPS |
|
Image Super-Resolution (SP)
|
100% |
287
10.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
452
16.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
438
16.2 IPS |
|
Text Classification (SP)
|
35% |
10
102.1 IPS |
|
Text Classification (HP)
|
35% |
19
169.6 IPS |
|
Text Classification (Q)
|
35% |
18
164.9 IPS |
|
Machine Translation (SP)
|
100% |
176
3.04 IPS |
|
Machine Translation (HP)
|
97% |
127
2.20 IPS |
|
Machine Translation (Q)
|
64% |
107
2.19 IPS |