Upload Date | January 21 2024 01:06 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-G990B2 |
Model ID | samsung SM-G990B2 |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM SM8350 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 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 | 7.19 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
269
50.3 IPS |
|
Image Classification (F16)
|
100% |
272
51.0 IPS |
|
Image Classification (I8)
|
97% |
651
121.9 IPS |
|
Image Segmentation (F32)
|
100% |
361
6.02 IPS |
|
Image Segmentation (F16)
|
100% |
364
6.08 IPS |
|
Image Segmentation (I8)
|
98% |
535
8.93 IPS |
|
Pose Estimation (F32)
|
100% |
560
0.68 IPS |
|
Pose Estimation (F16)
|
100% |
553
0.67 IPS |
|
Pose Estimation (I8)
|
100% |
2968
3.59 IPS |
|
Object Detection (F32)
|
100% |
293
21.9 IPS |
|
Object Detection (F16)
|
100% |
285
21.2 IPS |
|
Object Detection (I8)
|
61% |
821
61.3 IPS |
|
Face Detection (F32)
|
100% |
647
7.70 IPS |
|
Face Detection (F16)
|
100% |
635
7.56 IPS |
|
Face Detection (I8)
|
86% |
1460
17.4 IPS |
|
Depth Estimation (F32)
|
100% |
597
4.63 IPS |
|
Depth Estimation (F16)
|
100% |
613
4.75 IPS |
|
Depth Estimation (I8)
|
95% |
1598
12.4 IPS |
|
Style Transfer (F32)
|
100% |
1153
1.52 IPS |
|
Style Transfer (F16)
|
100% |
1174
1.54 IPS |
|
Style Transfer (I8)
|
98% |
2787
3.67 IPS |
|
Image Super-Resolution (F32)
|
100% |
392
14.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
388
13.9 IPS |
|
Image Super-Resolution (I8)
|
98% |
1535
54.8 IPS |
|
Text Classification (F32)
|
100% |
372
534.8 IPS |
|
Text Classification (F16)
|
100% |
378
542.7 IPS |
|
Text Classification (I8)
|
92% |
360
517.3 IPS |
|
Machine Translation (F32)
|
100% |
709
13.1 IPS |
|
Machine Translation (F16)
|
100% |
719
13.2 IPS |
|
Machine Translation (I8)
|
64% |
325
5.98 IPS |