Upload Date | July 18 2024 02:46 PM |
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 | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
661
123.8 IPS |
|
Image Classification (F16)
|
100% |
858
160.6 IPS |
|
Image Classification (I8)
|
99% |
574
107.5 IPS |
|
Image Segmentation (F32)
|
100% |
820
13.7 IPS |
|
Image Segmentation (F16)
|
100% |
1043
17.4 IPS |
|
Image Segmentation (I8)
|
98% |
1221
20.4 IPS |
|
Pose Estimation (F32)
|
100% |
968
1.17 IPS |
|
Pose Estimation (F16)
|
100% |
1388
1.68 IPS |
|
Pose Estimation (I8)
|
100% |
1379
1.67 IPS |
|
Object Detection (F32)
|
100% |
265
19.8 IPS |
|
Object Detection (F16)
|
100% |
265
19.8 IPS |
|
Object Detection (I8)
|
62% |
280
20.9 IPS |
|
Face Detection (F32)
|
100% |
2228
26.5 IPS |
|
Face Detection (F16)
|
97% |
2970
35.3 IPS |
|
Face Detection (I8)
|
86% |
2564
30.5 IPS |
|
Depth Estimation (F32)
|
100% |
1487
11.5 IPS |
|
Depth Estimation (F16)
|
100% |
2883
22.4 IPS |
|
Depth Estimation (I8)
|
95% |
2855
22.1 IPS |
|
Style Transfer (F32)
|
100% |
3785
4.98 IPS |
|
Style Transfer (F16)
|
100% |
8510
11.2 IPS |
|
Style Transfer (I8)
|
98% |
8017
10.5 IPS |
|
Image Super-Resolution (F32)
|
100% |
401
14.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
327
11.7 IPS |
|
Image Super-Resolution (I8)
|
98% |
390
13.9 IPS |
|
Text Classification (F32)
|
100% |
420
603.8 IPS |
|
Text Classification (F16)
|
100% |
419
602.3 IPS |
|
Text Classification (I8)
|
92% |
666
957.6 IPS |
|
Machine Translation (F32)
|
100% |
661
12.2 IPS |
|
Machine Translation (F16)
|
100% |
636
11.7 IPS |
|
Machine Translation (I8)
|
64% |
684
12.6 IPS |