User | M91 |
Upload Date | November 23 2024 02:23 PM |
Views | 2 |
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% |
121
22.4 IPS |
|
Image Classification (HP)
|
100% |
125
23.2 IPS |
|
Image Classification (Q)
|
100% |
200
37.2 IPS |
|
Image Segmentation (SP)
|
100% |
157
2.55 IPS |
|
Image Segmentation (HP)
|
100% |
162
2.63 IPS |
|
Image Segmentation (Q)
|
98% |
290
4.71 IPS |
|
Pose Estimation (SP)
|
100% |
533
0.62 IPS |
|
Pose Estimation (HP)
|
100% |
533
0.62 IPS |
|
Pose Estimation (Q)
|
84% |
430
0.51 IPS |
|
Object Detection (SP)
|
100% |
120
9.56 IPS |
|
Object Detection (HP)
|
100% |
117
9.32 IPS |
|
Object Detection (Q)
|
83% |
186
15.0 IPS |
|
Face Detection (SP)
|
100% |
287
3.42 IPS |
|
Face Detection (HP)
|
100% |
285
3.39 IPS |
|
Face Detection (Q)
|
95% |
512
6.11 IPS |
|
Depth Estimation (SP)
|
100% |
399
3.07 IPS |
|
Depth Estimation (HP)
|
99% |
408
3.14 IPS |
|
Depth Estimation (Q)
|
64% |
422
3.86 IPS |
|
Style Transfer (SP)
|
89% |
963
1.25 IPS |
|
Style Transfer (HP)
|
89% |
965
1.25 IPS |
|
Style Transfer (Q)
|
98% |
991
1.28 IPS |
|
Image Super-Resolution (SP)
|
100% |
178
6.57 IPS |
|
Image Super-Resolution (HP)
|
100% |
177
6.55 IPS |
|
Image Super-Resolution (Q)
|
97% |
244
9.03 IPS |
|
Text Classification (SP)
|
100% |
125
167.2 IPS |
|
Text Classification (HP)
|
100% |
119
158.4 IPS |
|
Text Classification (Q)
|
88% |
147
198.9 IPS |
|
Machine Translation (SP)
|
100% |
169
2.91 IPS |
|
Machine Translation (HP)
|
100% |
169
2.92 IPS |
|
Machine Translation (Q)
|
50% |
88
3.12 IPS |