Upload Date | November 23 2024 08:38 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | MediaTek Helio G80 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy A32 |
Model ID | samsung SM-A325N |
Motherboard | a32 |
CPU Information | |
---|---|
Name | ARM MT6769V/CT |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 3.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
99
18.4 IPS |
|
Image Classification (HP)
|
100% |
93
17.3 IPS |
|
Image Classification (Q)
|
100% |
197
36.6 IPS |
|
Image Segmentation (SP)
|
100% |
115
1.87 IPS |
|
Image Segmentation (HP)
|
100% |
117
1.90 IPS |
|
Image Segmentation (Q)
|
98% |
263
4.27 IPS |
|
Pose Estimation (SP)
|
100% |
437
0.51 IPS |
|
Pose Estimation (HP)
|
100% |
436
0.51 IPS |
|
Pose Estimation (Q)
|
84% |
356
0.42 IPS |
|
Object Detection (SP)
|
100% |
85
6.72 IPS |
|
Object Detection (HP)
|
100% |
85
6.75 IPS |
|
Object Detection (Q)
|
83% |
177
14.3 IPS |
|
Face Detection (SP)
|
100% |
270
3.20 IPS |
|
Face Detection (HP)
|
100% |
274
3.26 IPS |
|
Face Detection (Q)
|
95% |
472
5.63 IPS |
|
Depth Estimation (SP)
|
100% |
363
2.80 IPS |
|
Depth Estimation (HP)
|
99% |
369
2.84 IPS |
|
Depth Estimation (Q)
|
64% |
398
3.64 IPS |
|
Style Transfer (SP)
|
89% |
747
0.97 IPS |
|
Style Transfer (HP)
|
89% |
737
0.96 IPS |
|
Style Transfer (Q)
|
98% |
911
1.18 IPS |
|
Image Super-Resolution (SP)
|
100% |
182
6.74 IPS |
|
Image Super-Resolution (HP)
|
100% |
182
6.72 IPS |
|
Image Super-Resolution (Q)
|
97% |
208
7.70 IPS |
|
Text Classification (SP)
|
100% |
102
135.7 IPS |
|
Text Classification (HP)
|
100% |
101
135.2 IPS |
|
Text Classification (Q)
|
88% |
167
225.2 IPS |
|
Machine Translation (SP)
|
100% |
201
3.46 IPS |
|
Machine Translation (HP)
|
100% |
200
3.45 IPS |
|
Machine Translation (Q)
|
50% |
131
4.66 IPS |