Upload Date | March 27 2024 07:21 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy Note20 Ultra |
Model ID | samsung SM-N986B |
Motherboard | exynos990 |
Governor | energy_step |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 4 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.50 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 10.64 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
257
48.1 IPS |
|
Image Classification (F16)
|
100% |
251
47.0 IPS |
|
Image Classification (I8)
|
97% |
485
90.7 IPS |
|
Image Segmentation (F32)
|
100% |
326
5.44 IPS |
|
Image Segmentation (F16)
|
100% |
323
5.40 IPS |
|
Image Segmentation (I8)
|
98% |
428
7.15 IPS |
|
Pose Estimation (F32)
|
100% |
641
0.78 IPS |
|
Pose Estimation (F16)
|
100% |
604
0.73 IPS |
|
Pose Estimation (I8)
|
100% |
2936
3.56 IPS |
|
Object Detection (F32)
|
100% |
220
16.4 IPS |
|
Object Detection (F16)
|
100% |
231
17.3 IPS |
|
Object Detection (I8)
|
61% |
485
36.2 IPS |
|
Face Detection (F32)
|
100% |
521
6.19 IPS |
|
Face Detection (F16)
|
100% |
513
6.10 IPS |
|
Face Detection (I8)
|
86% |
777
9.24 IPS |
|
Depth Estimation (F32)
|
100% |
274
2.13 IPS |
|
Depth Estimation (F16)
|
100% |
421
3.26 IPS |
|
Depth Estimation (I8)
|
95% |
704
5.46 IPS |
|
Style Transfer (F32)
|
100% |
970
1.28 IPS |
|
Style Transfer (F16)
|
100% |
952
1.25 IPS |
|
Style Transfer (I8)
|
98% |
2678
3.52 IPS |
|
Image Super-Resolution (F32)
|
100% |
227
8.11 IPS |
|
Image Super-Resolution (F16)
|
100% |
391
14.0 IPS |
|
Image Super-Resolution (I8)
|
98% |
1116
39.9 IPS |
|
Text Classification (F32)
|
100% |
301
432.9 IPS |
|
Text Classification (F16)
|
100% |
307
441.6 IPS |
|
Text Classification (I8)
|
92% |
341
489.7 IPS |
|
Machine Translation (F32)
|
100% |
503
9.26 IPS |
|
Machine Translation (F16)
|
100% |
471
8.67 IPS |
|
Machine Translation (I8)
|
64% |
276
5.08 IPS |