Upload Date | January 10 2024 12:10 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S21+ 5G |
Model ID | samsung SM-G996B |
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 | 7.03 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
330
61.8 IPS |
|
Image Classification (F16)
|
100% |
592
110.8 IPS |
|
Image Classification (I8)
|
97% |
337
63.1 IPS |
|
Image Segmentation (F32)
|
100% |
579
9.67 IPS |
|
Image Segmentation (F16)
|
100% |
949
15.8 IPS |
|
Image Segmentation (I8)
|
98% |
921
15.4 IPS |
|
Pose Estimation (F32)
|
100% |
267
0.32 IPS |
|
Pose Estimation (F16)
|
100% |
339
0.41 IPS |
|
Pose Estimation (I8)
|
100% |
338
0.41 IPS |
|
Object Detection (F32)
|
100% |
350
26.1 IPS |
|
Object Detection (F16)
|
100% |
567
42.4 IPS |
|
Object Detection (I8)
|
62% |
508
38.0 IPS |
|
Face Detection (F32)
|
100% |
1428
17.0 IPS |
|
Face Detection (F16)
|
98% |
2120
25.2 IPS |
|
Face Detection (I8)
|
86% |
1960
23.3 IPS |
|
Depth Estimation (F32)
|
100% |
581
4.51 IPS |
|
Depth Estimation (F16)
|
100% |
761
5.90 IPS |
|
Depth Estimation (I8)
|
95% |
757
5.87 IPS |
|
Style Transfer (F32)
|
100% |
1211
1.59 IPS |
|
Style Transfer (F16)
|
100% |
2099
2.76 IPS |
|
Style Transfer (I8)
|
98% |
2101
2.76 IPS |
|
Image Super-Resolution (F32)
|
100% |
399
14.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
686
24.5 IPS |
|
Image Super-Resolution (I8)
|
98% |
669
23.9 IPS |
|
Text Classification (F32)
|
100% |
270
388.2 IPS |
|
Text Classification (F16)
|
100% |
268
384.9 IPS |
|
Text Classification (I8)
|
92% |
470
676.1 IPS |
|
Machine Translation (F32)
|
100% |
439
8.08 IPS |
|
Machine Translation (F16)
|
100% |
435
8.00 IPS |
|
Machine Translation (I8)
|
64% |
510
9.39 IPS |