Upload Date | November 22 2024 02:47 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6765V/CB |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A042F |
Model ID | samsung SM-A042F |
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% |
55
10.2 IPS |
|
Image Classification (HP)
|
100% |
72
13.4 IPS |
|
Image Classification (Q)
|
100% |
90
16.8 IPS |
|
Image Segmentation (SP)
|
100% |
92
1.49 IPS |
|
Image Segmentation (HP)
|
100% |
99
1.60 IPS |
|
Image Segmentation (Q)
|
98% |
179
2.91 IPS |
|
Pose Estimation (SP)
|
100% |
421
0.49 IPS |
|
Pose Estimation (HP)
|
100% |
372
0.43 IPS |
|
Pose Estimation (Q)
|
84% |
251
0.30 IPS |
|
Object Detection (SP)
|
100% |
74
5.90 IPS |
|
Object Detection (HP)
|
100% |
77
6.13 IPS |
|
Object Detection (Q)
|
83% |
113
9.16 IPS |
|
Face Detection (SP)
|
100% |
213
2.53 IPS |
|
Face Detection (HP)
|
100% |
207
2.45 IPS |
|
Face Detection (Q)
|
95% |
307
3.66 IPS |
|
Depth Estimation (SP)
|
100% |
278
2.14 IPS |
|
Depth Estimation (HP)
|
99% |
264
2.04 IPS |
|
Depth Estimation (Q)
|
64% |
239
2.19 IPS |
|
Style Transfer (SP)
|
89% |
671
0.87 IPS |
|
Style Transfer (HP)
|
89% |
660
0.86 IPS |
|
Style Transfer (Q)
|
98% |
608
0.78 IPS |
|
Image Super-Resolution (SP)
|
100% |
123
4.53 IPS |
|
Image Super-Resolution (HP)
|
100% |
124
4.58 IPS |
|
Image Super-Resolution (Q)
|
97% |
134
4.95 IPS |
|
Text Classification (SP)
|
100% |
77
102.4 IPS |
|
Text Classification (HP)
|
100% |
76
100.8 IPS |
|
Text Classification (Q)
|
88% |
82
110.2 IPS |
|
Machine Translation (SP)
|
100% |
112
1.93 IPS |
|
Machine Translation (HP)
|
100% |
112
1.92 IPS |
|
Machine Translation (Q)
|
50% |
52
1.85 IPS |