Upload Date | July 13 2024 02:45 PM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S21 FE |
Model ID | samsung SM-G990E |
Motherboard | exynos2100 |
Governor | energy_step |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 2.21 GHz |
Cluster 1 | 4 Cores @ 2.21 GHz |
Cluster 2 | 3 Cores @ 2.81 GHz |
Cluster 3 | 1 Core @ 2.91 GHz |
Memory Information | |
---|---|
Size | 7.13 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
57
10.7 IPS |
|
Image Classification (F16)
|
100% |
48
8.91 IPS |
|
Image Classification (I8)
|
97% |
58
10.8 IPS |
|
Image Segmentation (F32)
|
100% |
165
2.76 IPS |
|
Image Segmentation (F16)
|
100% |
160
2.66 IPS |
|
Image Segmentation (I8)
|
98% |
191
3.18 IPS |
|
Pose Estimation (F32)
|
100% |
445
0.54 IPS |
|
Pose Estimation (F16)
|
100% |
444
0.54 IPS |
|
Pose Estimation (I8)
|
100% |
2060
2.49 IPS |
|
Object Detection (F32)
|
100% |
73
5.43 IPS |
|
Object Detection (F16)
|
100% |
74
5.52 IPS |
|
Object Detection (I8)
|
61% |
86
6.42 IPS |
|
Face Detection (F32)
|
100% |
191
2.27 IPS |
|
Face Detection (F16)
|
100% |
205
2.43 IPS |
|
Face Detection (I8)
|
86% |
270
3.21 IPS |
|
Depth Estimation (F32)
|
100% |
281
2.18 IPS |
|
Depth Estimation (F16)
|
100% |
295
2.29 IPS |
|
Depth Estimation (I8)
|
95% |
317
2.46 IPS |
|
Style Transfer (F32)
|
100% |
906
1.19 IPS |
|
Style Transfer (F16)
|
100% |
843
1.11 IPS |
|
Style Transfer (I8)
|
98% |
1453
1.91 IPS |
|
Image Super-Resolution (F32)
|
100% |
202
7.20 IPS |
|
Image Super-Resolution (F16)
|
100% |
234
8.36 IPS |
|
Image Super-Resolution (I8)
|
98% |
222
7.93 IPS |
|
Text Classification (F32)
|
100% |
66
94.6 IPS |
|
Text Classification (F16)
|
100% |
47
68.2 IPS |
|
Text Classification (I8)
|
92% |
200
286.9 IPS |
|
Machine Translation (F32)
|
100% |
34
0.62 IPS |
|
Machine Translation (F16)
|
100% |
33
0.61 IPS |
|
Machine Translation (I8)
|
64% |
32
0.59 IPS |