Upload Date | June 29 2024 05:04 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-F946N |
Model ID | samsung SM-F946N |
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 | 10.87 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
293
54.9 IPS |
|
Image Classification (F16)
|
100% |
288
53.8 IPS |
|
Image Classification (I8)
|
97% |
709
132.6 IPS |
|
Image Segmentation (F32)
|
100% |
344
5.75 IPS |
|
Image Segmentation (F16)
|
100% |
342
5.71 IPS |
|
Image Segmentation (I8)
|
98% |
706
11.8 IPS |
|
Pose Estimation (F32)
|
100% |
472
0.57 IPS |
|
Pose Estimation (F16)
|
100% |
469
0.57 IPS |
|
Pose Estimation (I8)
|
100% |
1918
2.32 IPS |
|
Object Detection (F32)
|
100% |
287
21.5 IPS |
|
Object Detection (F16)
|
100% |
302
22.5 IPS |
|
Object Detection (I8)
|
61% |
820
61.2 IPS |
|
Face Detection (F32)
|
100% |
695
8.27 IPS |
|
Face Detection (F16)
|
100% |
674
8.01 IPS |
|
Face Detection (I8)
|
86% |
1512
18.0 IPS |
|
Depth Estimation (F32)
|
100% |
591
4.58 IPS |
|
Depth Estimation (F16)
|
100% |
585
4.54 IPS |
|
Depth Estimation (I8)
|
95% |
1575
12.2 IPS |
|
Style Transfer (F32)
|
100% |
923
1.21 IPS |
|
Style Transfer (F16)
|
100% |
812
1.07 IPS |
|
Style Transfer (I8)
|
98% |
1966
2.59 IPS |
|
Image Super-Resolution (F32)
|
100% |
261
9.33 IPS |
|
Image Super-Resolution (F16)
|
100% |
259
9.24 IPS |
|
Image Super-Resolution (I8)
|
98% |
892
31.9 IPS |
|
Text Classification (F32)
|
100% |
294
423.0 IPS |
|
Text Classification (F16)
|
100% |
294
422.2 IPS |
|
Text Classification (I8)
|
92% |
425
610.7 IPS |
|
Machine Translation (F32)
|
100% |
548
10.1 IPS |
|
Machine Translation (F16)
|
100% |
542
9.98 IPS |
|
Machine Translation (I8)
|
64% |
489
9.00 IPS |