Upload Date | January 04 2025 12:55 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6765V/CB |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A042M |
Model ID | samsung SM-A042M |
Motherboard | a04e |
CPU Information | |
---|---|
Name | ARM MT6765V/CB |
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 | 2.71 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
146
27.2 IPS |
|
Image Classification (HP)
|
100% |
140
26.1 IPS |
|
Image Classification (Q)
|
100% |
210
39.0 IPS |
|
Image Segmentation (SP)
|
100% |
173
2.80 IPS |
|
Image Segmentation (HP)
|
100% |
177
2.88 IPS |
|
Image Segmentation (Q)
|
98% |
329
5.34 IPS |
|
Pose Estimation (SP)
|
100% |
603
0.70 IPS |
|
Pose Estimation (HP)
|
100% |
562
0.66 IPS |
|
Pose Estimation (Q)
|
84% |
401
0.48 IPS |
|
Object Detection (SP)
|
100% |
118
9.37 IPS |
|
Object Detection (HP)
|
100% |
114
9.03 IPS |
|
Object Detection (Q)
|
83% |
171
13.8 IPS |
|
Face Detection (SP)
|
100% |
296
3.52 IPS |
|
Face Detection (HP)
|
100% |
289
3.44 IPS |
|
Face Detection (Q)
|
95% |
456
5.44 IPS |
|
Depth Estimation (SP)
|
100% |
385
2.96 IPS |
|
Depth Estimation (HP)
|
99% |
382
2.94 IPS |
|
Depth Estimation (Q)
|
64% |
340
3.12 IPS |
|
Style Transfer (SP)
|
89% |
864
1.12 IPS |
|
Style Transfer (HP)
|
89% |
861
1.12 IPS |
|
Style Transfer (Q)
|
98% |
871
1.12 IPS |
|
Image Super-Resolution (SP)
|
100% |
161
5.96 IPS |
|
Image Super-Resolution (HP)
|
100% |
157
5.78 IPS |
|
Image Super-Resolution (Q)
|
97% |
194
7.17 IPS |
|
Text Classification (SP)
|
100% |
82
108.8 IPS |
|
Text Classification (HP)
|
100% |
115
153.9 IPS |
|
Text Classification (Q)
|
88% |
134
180.8 IPS |
|
Machine Translation (SP)
|
100% |
139
2.40 IPS |
|
Machine Translation (HP)
|
100% |
141
2.42 IPS |
|
Machine Translation (Q)
|
50% |
65
2.29 IPS |