Upload Date | May 09 2024 11:37 AM |
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 | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
170
31.8 IPS |
|
Image Classification (F16)
|
100% |
166
31.0 IPS |
|
Image Classification (I8)
|
97% |
463
86.7 IPS |
|
Image Segmentation (F32)
|
100% |
386
6.45 IPS |
|
Image Segmentation (F16)
|
100% |
510
8.52 IPS |
|
Image Segmentation (I8)
|
98% |
478
7.98 IPS |
|
Pose Estimation (F32)
|
100% |
1532
1.85 IPS |
|
Pose Estimation (F16)
|
100% |
6278
7.60 IPS |
|
Pose Estimation (I8)
|
100% |
1264
1.53 IPS |
|
Object Detection (F32)
|
100% |
170
12.7 IPS |
|
Object Detection (F16)
|
100% |
171
12.8 IPS |
|
Object Detection (I8)
|
61% |
522
38.9 IPS |
|
Face Detection (F32)
|
100% |
415
4.94 IPS |
|
Face Detection (F16)
|
100% |
403
4.79 IPS |
|
Face Detection (I8)
|
86% |
958
11.4 IPS |
|
Depth Estimation (F32)
|
100% |
360
2.79 IPS |
|
Depth Estimation (F16)
|
100% |
355
2.76 IPS |
|
Depth Estimation (I8)
|
95% |
1123
8.71 IPS |
|
Style Transfer (F32)
|
100% |
727
0.96 IPS |
|
Style Transfer (F16)
|
100% |
726
0.96 IPS |
|
Style Transfer (I8)
|
98% |
618
0.81 IPS |
|
Image Super-Resolution (F32)
|
100% |
416
14.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
650
23.2 IPS |
|
Image Super-Resolution (I8)
|
98% |
852
30.4 IPS |
|
Text Classification (F32)
|
100% |
80
114.3 IPS |
|
Text Classification (F16)
|
100% |
85
121.7 IPS |
|
Text Classification (I8)
|
92% |
59
85.1 IPS |
|
Machine Translation (F32)
|
100% |
420
7.72 IPS |
|
Machine Translation (F16)
|
100% |
395
7.28 IPS |
|
Machine Translation (I8)
|
64% |
463
8.51 IPS |