Upload Date | September 18 2024 12:59 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT8768WT |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-T220 |
Model ID | samsung SM-T220 |
Motherboard | gta7litewifi |
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 | 2.79 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
91
17.0 IPS |
|
Image Classification (HP)
|
100% |
87
16.1 IPS |
|
Image Classification (Q)
|
100% |
160
29.7 IPS |
|
Image Segmentation (SP)
|
100% |
132
2.14 IPS |
|
Image Segmentation (HP)
|
100% |
127
2.06 IPS |
|
Image Segmentation (Q)
|
98% |
200
3.26 IPS |
|
Pose Estimation (SP)
|
100% |
477
0.56 IPS |
|
Pose Estimation (HP)
|
100% |
467
0.54 IPS |
|
Pose Estimation (Q)
|
84% |
350
0.42 IPS |
|
Object Detection (SP)
|
100% |
86
6.81 IPS |
|
Object Detection (HP)
|
100% |
101
7.97 IPS |
|
Object Detection (Q)
|
83% |
120
9.73 IPS |
|
Face Detection (SP)
|
100% |
244
2.90 IPS |
|
Face Detection (HP)
|
100% |
217
2.58 IPS |
|
Face Detection (Q)
|
95% |
391
4.66 IPS |
|
Depth Estimation (SP)
|
100% |
307
2.37 IPS |
|
Depth Estimation (HP)
|
99% |
297
2.29 IPS |
|
Depth Estimation (Q)
|
64% |
367
3.37 IPS |
|
Style Transfer (SP)
|
89% |
872
1.13 IPS |
|
Style Transfer (HP)
|
89% |
817
1.06 IPS |
|
Style Transfer (Q)
|
98% |
824
1.06 IPS |
|
Image Super-Resolution (SP)
|
100% |
149
5.52 IPS |
|
Image Super-Resolution (HP)
|
100% |
149
5.51 IPS |
|
Image Super-Resolution (Q)
|
97% |
207
7.67 IPS |
|
Text Classification (SP)
|
100% |
94
125.7 IPS |
|
Text Classification (HP)
|
100% |
97
130.1 IPS |
|
Text Classification (Q)
|
88% |
86
116.1 IPS |
|
Machine Translation (SP)
|
100% |
105
1.81 IPS |
|
Machine Translation (HP)
|
100% |
123
2.13 IPS |
|
Machine Translation (Q)
|
50% |
52
1.85 IPS |