Upload Date | September 19 2024 12:35 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT8768WT |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-T227U |
Model ID | samsung SM-T227U |
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 | 2.67 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
125
23.3 IPS |
|
Image Classification (HP)
|
100% |
122
22.7 IPS |
|
Image Classification (Q)
|
100% |
207
38.6 IPS |
|
Image Segmentation (SP)
|
100% |
160
2.59 IPS |
|
Image Segmentation (HP)
|
100% |
156
2.53 IPS |
|
Image Segmentation (Q)
|
98% |
286
4.64 IPS |
|
Pose Estimation (SP)
|
100% |
542
0.63 IPS |
|
Pose Estimation (HP)
|
100% |
539
0.63 IPS |
|
Pose Estimation (Q)
|
84% |
430
0.51 IPS |
|
Object Detection (SP)
|
100% |
121
9.60 IPS |
|
Object Detection (HP)
|
100% |
121
9.63 IPS |
|
Object Detection (Q)
|
83% |
189
15.3 IPS |
|
Face Detection (SP)
|
100% |
282
3.36 IPS |
|
Face Detection (HP)
|
100% |
283
3.36 IPS |
|
Face Detection (Q)
|
95% |
484
5.78 IPS |
|
Depth Estimation (SP)
|
100% |
398
3.07 IPS |
|
Depth Estimation (HP)
|
99% |
338
2.60 IPS |
|
Depth Estimation (Q)
|
64% |
417
3.82 IPS |
|
Style Transfer (SP)
|
89% |
948
1.23 IPS |
|
Style Transfer (HP)
|
89% |
981
1.27 IPS |
|
Style Transfer (Q)
|
98% |
987
1.27 IPS |
|
Image Super-Resolution (SP)
|
100% |
177
6.54 IPS |
|
Image Super-Resolution (HP)
|
100% |
164
6.07 IPS |
|
Image Super-Resolution (Q)
|
97% |
250
9.28 IPS |
|
Text Classification (SP)
|
100% |
119
159.2 IPS |
|
Text Classification (HP)
|
100% |
120
159.7 IPS |
|
Text Classification (Q)
|
88% |
138
186.3 IPS |
|
Machine Translation (SP)
|
100% |
169
2.92 IPS |
|
Machine Translation (HP)
|
100% |
167
2.88 IPS |
|
Machine Translation (Q)
|
50% |
87
3.09 IPS |