Upload Date | April 30 2025 05:28 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% |
134
24.9 IPS |
|
Image Classification (HP)
|
100% |
113
21.1 IPS |
|
Image Classification (Q)
|
100% |
219
40.7 IPS |
|
Image Segmentation (SP)
|
100% |
160
2.60 IPS |
|
Image Segmentation (HP)
|
100% |
157
2.55 IPS |
|
Image Segmentation (Q)
|
98% |
264
4.30 IPS |
|
Pose Estimation (SP)
|
100% |
627
0.73 IPS |
|
Pose Estimation (HP)
|
100% |
621
0.72 IPS |
|
Pose Estimation (Q)
|
84% |
570
0.68 IPS |
|
Object Detection (SP)
|
100% |
127
10.1 IPS |
|
Object Detection (HP)
|
100% |
126
9.99 IPS |
|
Object Detection (Q)
|
83% |
214
17.3 IPS |
|
Face Detection (SP)
|
100% |
336
4.00 IPS |
|
Face Detection (HP)
|
100% |
333
3.96 IPS |
|
Face Detection (Q)
|
95% |
562
6.71 IPS |
|
Depth Estimation (SP)
|
100% |
434
3.34 IPS |
|
Depth Estimation (HP)
|
99% |
471
3.63 IPS |
|
Depth Estimation (Q)
|
64% |
567
5.19 IPS |
|
Style Transfer (SP)
|
89% |
1205
1.56 IPS |
|
Style Transfer (HP)
|
89% |
1165
1.51 IPS |
|
Style Transfer (Q)
|
98% |
1507
1.94 IPS |
|
Image Super-Resolution (SP)
|
100% |
217
8.01 IPS |
|
Image Super-Resolution (HP)
|
100% |
217
8.00 IPS |
|
Image Super-Resolution (Q)
|
97% |
230
8.51 IPS |
|
Text Classification (SP)
|
100% |
116
154.6 IPS |
|
Text Classification (HP)
|
100% |
113
151.0 IPS |
|
Text Classification (Q)
|
88% |
125
168.8 IPS |
|
Machine Translation (SP)
|
100% |
171
2.94 IPS |
|
Machine Translation (HP)
|
100% |
172
2.96 IPS |
|
Machine Translation (Q)
|
50% |
80
2.82 IPS |