Upload Date | December 28 2024 10:44 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% |
109
20.3 IPS |
|
Image Classification (HP)
|
100% |
106
19.8 IPS |
|
Image Classification (Q)
|
100% |
164
30.4 IPS |
|
Image Segmentation (SP)
|
100% |
157
2.55 IPS |
|
Image Segmentation (HP)
|
100% |
155
2.52 IPS |
|
Image Segmentation (Q)
|
98% |
241
3.91 IPS |
|
Pose Estimation (SP)
|
100% |
589
0.69 IPS |
|
Pose Estimation (HP)
|
100% |
564
0.66 IPS |
|
Pose Estimation (Q)
|
84% |
584
0.69 IPS |
|
Object Detection (SP)
|
100% |
112
8.86 IPS |
|
Object Detection (HP)
|
100% |
116
9.22 IPS |
|
Object Detection (Q)
|
83% |
172
13.9 IPS |
|
Face Detection (SP)
|
100% |
291
3.46 IPS |
|
Face Detection (HP)
|
100% |
291
3.46 IPS |
|
Face Detection (Q)
|
95% |
435
5.20 IPS |
|
Depth Estimation (SP)
|
100% |
379
2.92 IPS |
|
Depth Estimation (HP)
|
99% |
370
2.85 IPS |
|
Depth Estimation (Q)
|
64% |
442
4.04 IPS |
|
Style Transfer (SP)
|
89% |
1199
1.56 IPS |
|
Style Transfer (HP)
|
89% |
1214
1.58 IPS |
|
Style Transfer (Q)
|
98% |
1391
1.79 IPS |
|
Image Super-Resolution (SP)
|
100% |
201
7.44 IPS |
|
Image Super-Resolution (HP)
|
100% |
198
7.32 IPS |
|
Image Super-Resolution (Q)
|
97% |
260
9.62 IPS |
|
Text Classification (SP)
|
100% |
110
146.4 IPS |
|
Text Classification (HP)
|
100% |
97
129.0 IPS |
|
Text Classification (Q)
|
88% |
110
147.8 IPS |
|
Machine Translation (SP)
|
100% |
140
2.41 IPS |
|
Machine Translation (HP)
|
100% |
139
2.39 IPS |
|
Machine Translation (Q)
|
50% |
68
2.40 IPS |