Upload Date | July 13 2024 04:13 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A546E |
Model ID | samsung SM-A546E |
Motherboard | s5e8835 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
145
27.1 IPS |
|
Image Classification (F16)
|
100% |
137
25.7 IPS |
|
Image Classification (I8)
|
97% |
176
33.0 IPS |
|
Image Segmentation (F32)
|
100% |
275
4.59 IPS |
|
Image Segmentation (F16)
|
100% |
197
3.29 IPS |
|
Image Segmentation (I8)
|
98% |
234
3.91 IPS |
|
Pose Estimation (F32)
|
100% |
372
0.45 IPS |
|
Pose Estimation (F16)
|
100% |
368
0.45 IPS |
|
Pose Estimation (I8)
|
100% |
1559
1.89 IPS |
|
Object Detection (F32)
|
100% |
86
6.41 IPS |
|
Object Detection (F16)
|
100% |
90
6.69 IPS |
|
Object Detection (I8)
|
61% |
129
9.64 IPS |
|
Face Detection (F32)
|
100% |
243
2.89 IPS |
|
Face Detection (F16)
|
100% |
235
2.80 IPS |
|
Face Detection (I8)
|
86% |
300
3.56 IPS |
|
Depth Estimation (F32)
|
100% |
249
1.93 IPS |
|
Depth Estimation (F16)
|
100% |
223
1.73 IPS |
|
Depth Estimation (I8)
|
95% |
440
3.41 IPS |
|
Style Transfer (F32)
|
100% |
665
0.87 IPS |
|
Style Transfer (F16)
|
100% |
678
0.89 IPS |
|
Style Transfer (I8)
|
98% |
1399
1.84 IPS |
|
Image Super-Resolution (F32)
|
100% |
119
4.24 IPS |
|
Image Super-Resolution (F16)
|
100% |
145
5.16 IPS |
|
Image Super-Resolution (I8)
|
98% |
295
10.5 IPS |
|
Text Classification (F32)
|
100% |
208
299.6 IPS |
|
Text Classification (F16)
|
100% |
291
418.5 IPS |
|
Text Classification (I8)
|
92% |
297
426.8 IPS |
|
Machine Translation (F32)
|
100% |
95
1.75 IPS |
|
Machine Translation (F16)
|
100% |
66
1.22 IPS |
|
Machine Translation (I8)
|
64% |
52
0.96 IPS |