Upload Date | June 17 2025 04:43 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 662 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy Tab A7 |
Model ID | samsung SM-T500 |
Motherboard | bengal |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.02 GHz |
Memory Information | |
---|---|
Size | 2.64 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
151
28.1 IPS |
|
Image Classification (HP)
|
100% |
144
26.7 IPS |
|
Image Classification (Q)
|
100% |
214
39.9 IPS |
|
Image Segmentation (SP)
|
100% |
184
2.99 IPS |
|
Image Segmentation (HP)
|
100% |
182
2.94 IPS |
|
Image Segmentation (Q)
|
98% |
295
4.80 IPS |
|
Pose Estimation (SP)
|
100% |
666
0.78 IPS |
|
Pose Estimation (HP)
|
100% |
650
0.76 IPS |
|
Pose Estimation (Q)
|
84% |
574
0.68 IPS |
|
Object Detection (SP)
|
100% |
139
11.0 IPS |
|
Object Detection (HP)
|
100% |
138
11.0 IPS |
|
Object Detection (Q)
|
83% |
203
16.4 IPS |
|
Face Detection (SP)
|
100% |
364
4.32 IPS |
|
Face Detection (HP)
|
100% |
366
4.35 IPS |
|
Face Detection (Q)
|
95% |
519
6.19 IPS |
|
Depth Estimation (SP)
|
100% |
476
3.67 IPS |
|
Depth Estimation (HP)
|
99% |
487
3.75 IPS |
|
Depth Estimation (Q)
|
64% |
495
4.53 IPS |
|
Style Transfer (SP)
|
89% |
1326
1.72 IPS |
|
Style Transfer (HP)
|
89% |
1315
1.71 IPS |
|
Style Transfer (Q)
|
98% |
1210
1.56 IPS |
|
Image Super-Resolution (SP)
|
100% |
218
8.04 IPS |
|
Image Super-Resolution (HP)
|
100% |
215
7.94 IPS |
|
Image Super-Resolution (Q)
|
97% |
287
10.6 IPS |
|
Text Classification (SP)
|
100% |
140
186.7 IPS |
|
Text Classification (HP)
|
100% |
140
186.3 IPS |
|
Text Classification (Q)
|
88% |
159
215.0 IPS |
|
Machine Translation (SP)
|
100% |
180
3.10 IPS |
|
Machine Translation (HP)
|
100% |
178
3.06 IPS |
|
Machine Translation (Q)
|
50% |
91
3.22 IPS |