Upload Date | September 20 2024 05:08 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A155F |
Model ID | samsung SM-A155F |
Motherboard | a15 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.20 GHz |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
118
21.9 IPS |
|
Image Classification (HP)
|
100% |
353
65.7 IPS |
|
Image Classification (Q)
|
97% |
68
12.7 IPS |
|
Image Segmentation (SP)
|
100% |
220
3.57 IPS |
|
Image Segmentation (HP)
|
100% |
145
2.35 IPS |
|
Image Segmentation (Q)
|
98% |
85
1.38 IPS |
|
Pose Estimation (SP)
|
100% |
777
0.91 IPS |
|
Pose Estimation (HP)
|
98% |
1870
2.19 IPS |
|
Pose Estimation (Q)
|
70% |
1045
1.33 IPS |
|
Object Detection (SP)
|
100% |
138
10.9 IPS |
|
Object Detection (HP)
|
100% |
107
8.47 IPS |
|
Object Detection (Q)
|
80% |
83
6.73 IPS |
|
Face Detection (SP)
|
28% |
34
6.30 IPS |
|
Face Detection (HP)
|
100% |
280
3.33 IPS |
|
Face Detection (Q)
|
97% |
130
1.55 IPS |
|
Depth Estimation (SP)
|
100% |
343
2.65 IPS |
|
Depth Estimation (HP)
|
99% |
236
1.82 IPS |
|
Depth Estimation (Q)
|
57% |
243
2.65 IPS |
|
Style Transfer (SP)
|
100% |
679
0.87 IPS |
|
Style Transfer (HP)
|
100% |
393
0.51 IPS |
|
Style Transfer (Q)
|
98% |
1585
2.04 IPS |
|
Image Super-Resolution (SP)
|
100% |
344
12.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
733
27.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
390
14.5 IPS |
|
Text Classification (SP)
|
100% |
82
109.4 IPS |
|
Text Classification (HP)
|
100% |
159
212.1 IPS |
|
Text Classification (Q)
|
93% |
83
110.9 IPS |
|
Machine Translation (SP)
|
100% |
212
3.66 IPS |
|
Machine Translation (HP)
|
100% |
269
4.63 IPS |
|
Machine Translation (Q)
|
55% |
104
2.75 IPS |