Upload Date | June 15 2025 02:53 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% |
147
27.4 IPS |
|
Image Classification (HP)
|
100% |
148
27.5 IPS |
|
Image Classification (Q)
|
100% |
219
40.7 IPS |
|
Image Segmentation (SP)
|
100% |
190
3.09 IPS |
|
Image Segmentation (HP)
|
100% |
189
3.06 IPS |
|
Image Segmentation (Q)
|
98% |
298
4.85 IPS |
|
Pose Estimation (SP)
|
100% |
690
0.81 IPS |
|
Pose Estimation (HP)
|
100% |
682
0.80 IPS |
|
Pose Estimation (Q)
|
84% |
639
0.76 IPS |
|
Object Detection (SP)
|
100% |
150
11.9 IPS |
|
Object Detection (HP)
|
100% |
154
12.2 IPS |
|
Object Detection (Q)
|
83% |
224
18.1 IPS |
|
Face Detection (SP)
|
100% |
372
4.42 IPS |
|
Face Detection (HP)
|
100% |
364
4.32 IPS |
|
Face Detection (Q)
|
95% |
545
6.51 IPS |
|
Depth Estimation (SP)
|
100% |
499
3.85 IPS |
|
Depth Estimation (HP)
|
99% |
460
3.55 IPS |
|
Depth Estimation (Q)
|
64% |
553
5.06 IPS |
|
Style Transfer (SP)
|
89% |
1238
1.61 IPS |
|
Style Transfer (HP)
|
89% |
1370
1.78 IPS |
|
Style Transfer (Q)
|
98% |
1571
2.03 IPS |
|
Image Super-Resolution (SP)
|
100% |
248
9.16 IPS |
|
Image Super-Resolution (HP)
|
100% |
218
8.06 IPS |
|
Image Super-Resolution (Q)
|
97% |
299
11.1 IPS |
|
Text Classification (SP)
|
100% |
142
189.8 IPS |
|
Text Classification (HP)
|
100% |
142
189.7 IPS |
|
Text Classification (Q)
|
88% |
157
211.3 IPS |
|
Machine Translation (SP)
|
100% |
184
3.17 IPS |
|
Machine Translation (HP)
|
100% |
182
3.14 IPS |
|
Machine Translation (Q)
|
50% |
93
3.32 IPS |