Upload Date | March 05 2025 10:06 PM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 670 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy Tab S5e |
Model ID | samsung SM-T720 |
Motherboard | sdm710 |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 6 part 2050 revision 13 |
Base Frequency | 1.71 GHz |
Cluster 1 | 6 Cores @ 1.71 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
60
11.2 IPS |
|
Image Classification (HP)
|
100% |
103
19.1 IPS |
|
Image Classification (Q)
|
97% |
108
20.2 IPS |
|
Image Segmentation (SP)
|
100% |
82
1.33 IPS |
|
Image Segmentation (HP)
|
100% |
151
2.45 IPS |
|
Image Segmentation (Q)
|
98% |
149
2.43 IPS |
|
Pose Estimation (SP)
|
100% |
117
0.14 IPS |
|
Pose Estimation (HP)
|
100% |
184
0.21 IPS |
|
Pose Estimation (Q)
|
95% |
183
0.22 IPS |
|
Object Detection (SP)
|
100% |
54
4.27 IPS |
|
Object Detection (HP)
|
100% |
87
6.90 IPS |
|
Object Detection (Q)
|
89% |
90
7.24 IPS |
|
Face Detection (SP)
|
100% |
146
1.73 IPS |
|
Face Detection (HP)
|
100% |
268
3.19 IPS |
|
Face Detection (Q)
|
97% |
284
3.39 IPS |
|
Depth Estimation (SP)
|
100% |
143
1.10 IPS |
|
Depth Estimation (HP)
|
99% |
262
2.02 IPS |
|
Depth Estimation (Q)
|
62% |
215
2.04 IPS |
|
Style Transfer (SP)
|
100% |
276
0.35 IPS |
|
Style Transfer (HP)
|
100% |
636
0.82 IPS |
|
Style Transfer (Q)
|
98% |
631
0.81 IPS |
|
Image Super-Resolution (SP)
|
100% |
70
2.60 IPS |
|
Image Super-Resolution (HP)
|
100% |
130
4.79 IPS |
|
Image Super-Resolution (Q)
|
97% |
128
4.75 IPS |
|
Text Classification (SP)
|
100% |
73
98.1 IPS |
|
Text Classification (HP)
|
100% |
73
97.2 IPS |
|
Text Classification (Q)
|
91% |
85
114.8 IPS |
|
Machine Translation (SP)
|
100% |
130
2.23 IPS |
|
Machine Translation (HP)
|
100% |
129
2.22 IPS |
|
Machine Translation (Q)
|
57% |
83
2.02 IPS |