Upload Date | October 19 2024 05:44 PM |
Views | 4 |
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% |
107
20.0 IPS |
|
Image Classification (HP)
|
100% |
103
19.2 IPS |
|
Image Classification (Q)
|
100% |
184
34.2 IPS |
|
Image Segmentation (SP)
|
100% |
134
2.18 IPS |
|
Image Segmentation (HP)
|
100% |
135
2.19 IPS |
|
Image Segmentation (Q)
|
98% |
212
3.46 IPS |
|
Pose Estimation (SP)
|
100% |
538
0.63 IPS |
|
Pose Estimation (HP)
|
100% |
541
0.63 IPS |
|
Pose Estimation (Q)
|
84% |
457
0.54 IPS |
|
Object Detection (SP)
|
100% |
110
8.71 IPS |
|
Object Detection (HP)
|
100% |
106
8.39 IPS |
|
Object Detection (Q)
|
83% |
185
15.0 IPS |
|
Face Detection (SP)
|
100% |
305
3.62 IPS |
|
Face Detection (HP)
|
100% |
303
3.60 IPS |
|
Face Detection (Q)
|
95% |
460
5.50 IPS |
|
Depth Estimation (SP)
|
100% |
422
3.25 IPS |
|
Depth Estimation (HP)
|
99% |
339
2.61 IPS |
|
Depth Estimation (Q)
|
64% |
455
4.16 IPS |
|
Style Transfer (SP)
|
89% |
881
1.14 IPS |
|
Style Transfer (HP)
|
89% |
865
1.12 IPS |
|
Style Transfer (Q)
|
98% |
1198
1.55 IPS |
|
Image Super-Resolution (SP)
|
100% |
209
7.73 IPS |
|
Image Super-Resolution (HP)
|
100% |
182
6.71 IPS |
|
Image Super-Resolution (Q)
|
97% |
181
6.72 IPS |
|
Text Classification (SP)
|
100% |
100
133.8 IPS |
|
Text Classification (HP)
|
100% |
100
132.9 IPS |
|
Text Classification (Q)
|
88% |
116
156.7 IPS |
|
Machine Translation (SP)
|
100% |
153
2.64 IPS |
|
Machine Translation (HP)
|
100% |
153
2.63 IPS |
|
Machine Translation (Q)
|
50% |
71
2.54 IPS |