Upload Date | November 19 2024 08:22 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% |
84
15.6 IPS |
|
Image Classification (HP)
|
100% |
73
13.5 IPS |
|
Image Classification (Q)
|
100% |
125
23.3 IPS |
|
Image Segmentation (SP)
|
100% |
117
1.89 IPS |
|
Image Segmentation (HP)
|
100% |
106
1.72 IPS |
|
Image Segmentation (Q)
|
98% |
203
3.30 IPS |
|
Pose Estimation (SP)
|
100% |
381
0.44 IPS |
|
Pose Estimation (HP)
|
100% |
367
0.43 IPS |
|
Pose Estimation (Q)
|
84% |
301
0.36 IPS |
|
Object Detection (SP)
|
100% |
79
6.25 IPS |
|
Object Detection (HP)
|
100% |
78
6.22 IPS |
|
Object Detection (Q)
|
83% |
130
10.5 IPS |
|
Face Detection (SP)
|
100% |
182
2.16 IPS |
|
Face Detection (HP)
|
100% |
188
2.23 IPS |
|
Face Detection (Q)
|
95% |
339
4.05 IPS |
|
Depth Estimation (SP)
|
100% |
273
2.11 IPS |
|
Depth Estimation (HP)
|
99% |
273
2.10 IPS |
|
Depth Estimation (Q)
|
64% |
316
2.90 IPS |
|
Style Transfer (SP)
|
89% |
764
0.99 IPS |
|
Style Transfer (HP)
|
89% |
760
0.99 IPS |
|
Style Transfer (Q)
|
98% |
783
1.01 IPS |
|
Image Super-Resolution (SP)
|
100% |
112
4.14 IPS |
|
Image Super-Resolution (HP)
|
100% |
112
4.12 IPS |
|
Image Super-Resolution (Q)
|
97% |
181
6.69 IPS |
|
Text Classification (SP)
|
100% |
74
98.2 IPS |
|
Text Classification (HP)
|
100% |
78
103.4 IPS |
|
Text Classification (Q)
|
88% |
82
110.7 IPS |
|
Machine Translation (SP)
|
100% |
98
1.69 IPS |
|
Machine Translation (HP)
|
100% |
95
1.64 IPS |
|
Machine Translation (Q)
|
50% |
58
2.07 IPS |