Upload Date | May 29 2024 07:43 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy S20 FE 5G |
Model ID | samsung SM-G780G |
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% |
271
50.7 IPS |
|
Image Classification (F16)
|
100% |
300
56.2 IPS |
|
Image Classification (I8)
|
97% |
675
126.4 IPS |
|
Image Segmentation (F32)
|
100% |
382
6.39 IPS |
|
Image Segmentation (F16)
|
100% |
380
6.35 IPS |
|
Image Segmentation (I8)
|
98% |
500
8.34 IPS |
|
Pose Estimation (F32)
|
100% |
581
0.70 IPS |
|
Pose Estimation (F16)
|
100% |
606
0.73 IPS |
|
Pose Estimation (I8)
|
100% |
2573
3.12 IPS |
|
Object Detection (F32)
|
100% |
314
23.4 IPS |
|
Object Detection (F16)
|
100% |
358
26.7 IPS |
|
Object Detection (I8)
|
61% |
759
56.6 IPS |
|
Face Detection (F32)
|
100% |
638
7.59 IPS |
|
Face Detection (F16)
|
100% |
640
7.61 IPS |
|
Face Detection (I8)
|
86% |
1697
20.2 IPS |
|
Depth Estimation (F32)
|
100% |
567
4.40 IPS |
|
Depth Estimation (F16)
|
100% |
563
4.37 IPS |
|
Depth Estimation (I8)
|
95% |
1387
10.8 IPS |
|
Style Transfer (F32)
|
100% |
946
1.24 IPS |
|
Style Transfer (F16)
|
100% |
946
1.24 IPS |
|
Style Transfer (I8)
|
98% |
2771
3.64 IPS |
|
Image Super-Resolution (F32)
|
100% |
360
12.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
347
12.4 IPS |
|
Image Super-Resolution (I8)
|
98% |
1703
60.8 IPS |
|
Text Classification (F32)
|
100% |
299
429.3 IPS |
|
Text Classification (F16)
|
100% |
249
358.5 IPS |
|
Text Classification (I8)
|
92% |
277
398.4 IPS |
|
Machine Translation (F32)
|
100% |
642
11.8 IPS |
|
Machine Translation (F16)
|
100% |
680
12.5 IPS |
|
Machine Translation (I8)
|
64% |
319
5.88 IPS |