Upload Date | May 09 2024 12:17 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy S20 FE 5G |
Model ID | samsung SM-G781B |
Motherboard | kona |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 5.50 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
245
45.9 IPS |
|
Image Classification (F16)
|
100% |
247
46.2 IPS |
|
Image Classification (I8)
|
97% |
579
108.4 IPS |
|
Image Segmentation (F32)
|
100% |
360
6.02 IPS |
|
Image Segmentation (F16)
|
100% |
363
6.06 IPS |
|
Image Segmentation (I8)
|
98% |
471
7.87 IPS |
|
Pose Estimation (F32)
|
100% |
568
0.69 IPS |
|
Pose Estimation (F16)
|
100% |
561
0.68 IPS |
|
Pose Estimation (I8)
|
100% |
2626
3.18 IPS |
|
Object Detection (F32)
|
100% |
302
22.5 IPS |
|
Object Detection (F16)
|
100% |
300
22.4 IPS |
|
Object Detection (I8)
|
61% |
786
58.7 IPS |
|
Face Detection (F32)
|
100% |
604
7.19 IPS |
|
Face Detection (F16)
|
100% |
609
7.24 IPS |
|
Face Detection (I8)
|
86% |
1500
17.8 IPS |
|
Depth Estimation (F32)
|
100% |
542
4.21 IPS |
|
Depth Estimation (F16)
|
100% |
564
4.38 IPS |
|
Depth Estimation (I8)
|
95% |
1337
10.4 IPS |
|
Style Transfer (F32)
|
100% |
940
1.24 IPS |
|
Style Transfer (F16)
|
100% |
939
1.23 IPS |
|
Style Transfer (I8)
|
98% |
2756
3.62 IPS |
|
Image Super-Resolution (F32)
|
100% |
328
11.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
323
11.5 IPS |
|
Image Super-Resolution (I8)
|
98% |
1200
42.8 IPS |
|
Text Classification (F32)
|
100% |
321
461.7 IPS |
|
Text Classification (F16)
|
100% |
300
430.4 IPS |
|
Text Classification (I8)
|
92% |
268
385.1 IPS |
|
Machine Translation (F32)
|
100% |
638
11.7 IPS |
|
Machine Translation (F16)
|
100% |
648
11.9 IPS |
|
Machine Translation (I8)
|
64% |
305
5.62 IPS |