Upload Date | July 17 2024 06:24 PM |
Views | 1 |
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% |
211
39.5 IPS |
|
Image Classification (F16)
|
100% |
217
40.7 IPS |
|
Image Classification (I8)
|
97% |
68
12.6 IPS |
|
Image Segmentation (F32)
|
100% |
171
2.86 IPS |
|
Image Segmentation (F16)
|
100% |
171
2.86 IPS |
|
Image Segmentation (I8)
|
98% |
198
3.31 IPS |
|
Pose Estimation (F32)
|
100% |
447
0.54 IPS |
|
Pose Estimation (F16)
|
100% |
416
0.50 IPS |
|
Pose Estimation (I8)
|
100% |
1657
2.01 IPS |
|
Object Detection (F32)
|
100% |
101
7.56 IPS |
|
Object Detection (F16)
|
100% |
74
5.50 IPS |
|
Object Detection (I8)
|
61% |
85
6.34 IPS |
|
Face Detection (F32)
|
100% |
202
2.40 IPS |
|
Face Detection (F16)
|
100% |
205
2.44 IPS |
|
Face Detection (I8)
|
86% |
283
3.37 IPS |
|
Depth Estimation (F32)
|
100% |
255
1.98 IPS |
|
Depth Estimation (F16)
|
100% |
268
2.08 IPS |
|
Depth Estimation (I8)
|
95% |
291
2.25 IPS |
|
Style Transfer (F32)
|
100% |
909
1.20 IPS |
|
Style Transfer (F16)
|
100% |
867
1.14 IPS |
|
Style Transfer (I8)
|
98% |
1443
1.90 IPS |
|
Image Super-Resolution (F32)
|
100% |
139
4.95 IPS |
|
Image Super-Resolution (F16)
|
100% |
146
5.23 IPS |
|
Image Super-Resolution (I8)
|
98% |
408
14.6 IPS |
|
Text Classification (F32)
|
100% |
232
333.0 IPS |
|
Text Classification (F16)
|
100% |
252
362.6 IPS |
|
Text Classification (I8)
|
92% |
189
271.4 IPS |
|
Machine Translation (F32)
|
100% |
33
0.61 IPS |
|
Machine Translation (F16)
|
100% |
26
0.48 IPS |
|
Machine Translation (I8)
|
64% |
32
0.59 IPS |