Upload Date | July 06 2024 06:23 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S23 |
Model ID | samsung SM-S911B |
Motherboard | kalama |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 3 Cores @ 2.02 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Cluster 3 | 1 Core @ 3.36 GHz |
Memory Information | |
---|---|
Size | 6.89 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
288
53.8 IPS |
|
Image Classification (F16)
|
100% |
278
52.1 IPS |
|
Image Classification (I8)
|
97% |
702
131.3 IPS |
|
Image Segmentation (F32)
|
100% |
339
5.67 IPS |
|
Image Segmentation (F16)
|
100% |
337
5.63 IPS |
|
Image Segmentation (I8)
|
98% |
701
11.7 IPS |
|
Pose Estimation (F32)
|
100% |
468
0.57 IPS |
|
Pose Estimation (F16)
|
100% |
467
0.57 IPS |
|
Pose Estimation (I8)
|
100% |
1970
2.39 IPS |
|
Object Detection (F32)
|
100% |
293
21.9 IPS |
|
Object Detection (F16)
|
100% |
295
22.1 IPS |
|
Object Detection (I8)
|
61% |
825
61.6 IPS |
|
Face Detection (F32)
|
100% |
663
7.89 IPS |
|
Face Detection (F16)
|
100% |
656
7.80 IPS |
|
Face Detection (I8)
|
86% |
1516
18.0 IPS |
|
Depth Estimation (F32)
|
100% |
581
4.51 IPS |
|
Depth Estimation (F16)
|
100% |
581
4.50 IPS |
|
Depth Estimation (I8)
|
95% |
1698
13.2 IPS |
|
Style Transfer (F32)
|
100% |
918
1.21 IPS |
|
Style Transfer (F16)
|
100% |
919
1.21 IPS |
|
Style Transfer (I8)
|
98% |
2326
3.06 IPS |
|
Image Super-Resolution (F32)
|
100% |
329
11.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
330
11.8 IPS |
|
Image Super-Resolution (I8)
|
98% |
1179
42.1 IPS |
|
Text Classification (F32)
|
100% |
422
606.8 IPS |
|
Text Classification (F16)
|
100% |
426
611.6 IPS |
|
Text Classification (I8)
|
92% |
659
947.2 IPS |
|
Machine Translation (F32)
|
100% |
652
12.0 IPS |
|
Machine Translation (F16)
|
100% |
633
11.7 IPS |
|
Machine Translation (I8)
|
64% |
692
12.7 IPS |