Upload Date | December 19 2024 05:01 PM |
Views | 9 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT8768WT |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-T225 |
Model ID | samsung SM-T225 |
Motherboard | gta7lite |
CPU Information | |
---|---|
Name | ARM MT8768WT |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
Base Frequency | 2.30 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.30 GHz |
Memory Information | |
---|---|
Size | 2.69 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
73
13.6 IPS |
|
Image Classification (HP)
|
100% |
80
14.8 IPS |
|
Image Classification (Q)
|
100% |
113
21.0 IPS |
|
Image Segmentation (SP)
|
100% |
116
1.87 IPS |
|
Image Segmentation (HP)
|
100% |
111
1.79 IPS |
|
Image Segmentation (Q)
|
98% |
178
2.89 IPS |
|
Pose Estimation (SP)
|
100% |
392
0.46 IPS |
|
Pose Estimation (HP)
|
100% |
388
0.45 IPS |
|
Pose Estimation (Q)
|
84% |
303
0.36 IPS |
|
Object Detection (SP)
|
100% |
72
5.70 IPS |
|
Object Detection (HP)
|
100% |
81
6.45 IPS |
|
Object Detection (Q)
|
83% |
127
10.2 IPS |
|
Face Detection (SP)
|
100% |
162
1.93 IPS |
|
Face Detection (HP)
|
100% |
216
2.57 IPS |
|
Face Detection (Q)
|
95% |
373
4.45 IPS |
|
Depth Estimation (SP)
|
100% |
305
2.35 IPS |
|
Depth Estimation (HP)
|
99% |
279
2.15 IPS |
|
Depth Estimation (Q)
|
64% |
308
2.82 IPS |
|
Style Transfer (SP)
|
89% |
722
0.94 IPS |
|
Style Transfer (HP)
|
89% |
712
0.92 IPS |
|
Style Transfer (Q)
|
98% |
771
0.99 IPS |
|
Image Super-Resolution (SP)
|
100% |
126
4.65 IPS |
|
Image Super-Resolution (HP)
|
100% |
118
4.36 IPS |
|
Image Super-Resolution (Q)
|
97% |
181
6.70 IPS |
|
Text Classification (SP)
|
100% |
77
102.9 IPS |
|
Text Classification (HP)
|
100% |
75
100.5 IPS |
|
Text Classification (Q)
|
88% |
84
113.9 IPS |
|
Machine Translation (SP)
|
100% |
88
1.52 IPS |
|
Machine Translation (HP)
|
100% |
87
1.49 IPS |
|
Machine Translation (Q)
|
50% |
62
2.20 IPS |