Upload Date | April 27 2025 07:25 PM |
Views | 6 |
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% |
61
11.4 IPS |
|
Image Classification (HP)
|
100% |
62
11.6 IPS |
|
Image Classification (Q)
|
100% |
97
18.1 IPS |
|
Image Segmentation (SP)
|
100% |
94
1.52 IPS |
|
Image Segmentation (HP)
|
100% |
108
1.75 IPS |
|
Image Segmentation (Q)
|
98% |
143
2.33 IPS |
|
Pose Estimation (SP)
|
100% |
335
0.39 IPS |
|
Pose Estimation (HP)
|
100% |
324
0.38 IPS |
|
Pose Estimation (Q)
|
84% |
270
0.32 IPS |
|
Object Detection (SP)
|
100% |
66
5.20 IPS |
|
Object Detection (HP)
|
100% |
65
5.14 IPS |
|
Object Detection (Q)
|
83% |
104
8.43 IPS |
|
Face Detection (SP)
|
100% |
178
2.12 IPS |
|
Face Detection (HP)
|
100% |
178
2.11 IPS |
|
Face Detection (Q)
|
95% |
299
3.56 IPS |
|
Depth Estimation (SP)
|
100% |
237
1.82 IPS |
|
Depth Estimation (HP)
|
99% |
221
1.70 IPS |
|
Depth Estimation (Q)
|
64% |
249
2.28 IPS |
|
Style Transfer (SP)
|
89% |
676
0.88 IPS |
|
Style Transfer (HP)
|
89% |
628
0.81 IPS |
|
Style Transfer (Q)
|
98% |
646
0.83 IPS |
|
Image Super-Resolution (SP)
|
100% |
91
3.37 IPS |
|
Image Super-Resolution (HP)
|
100% |
90
3.33 IPS |
|
Image Super-Resolution (Q)
|
97% |
133
4.92 IPS |
|
Text Classification (SP)
|
100% |
44
59.1 IPS |
|
Text Classification (HP)
|
100% |
44
59.2 IPS |
|
Text Classification (Q)
|
88% |
63
84.9 IPS |
|
Machine Translation (SP)
|
100% |
77
1.32 IPS |
|
Machine Translation (HP)
|
100% |
65
1.11 IPS |
|
Machine Translation (Q)
|
50% |
50
1.76 IPS |