Upload Date | January 05 2024 08:54 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-F946B |
Model ID | samsung SM-F946B |
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% |
287
53.7 IPS |
|
Image Classification (F16)
|
100% |
277
51.8 IPS |
|
Image Classification (I8)
|
97% |
707
132.3 IPS |
|
Image Segmentation (F32)
|
100% |
338
5.64 IPS |
|
Image Segmentation (F16)
|
100% |
334
5.58 IPS |
|
Image Segmentation (I8)
|
98% |
712
11.9 IPS |
|
Pose Estimation (F32)
|
100% |
463
0.56 IPS |
|
Pose Estimation (F16)
|
100% |
460
0.56 IPS |
|
Pose Estimation (I8)
|
100% |
1943
2.35 IPS |
|
Object Detection (F32)
|
100% |
295
22.0 IPS |
|
Object Detection (F16)
|
100% |
294
22.0 IPS |
|
Object Detection (I8)
|
61% |
816
60.9 IPS |
|
Face Detection (F32)
|
100% |
670
7.97 IPS |
|
Face Detection (F16)
|
100% |
662
7.88 IPS |
|
Face Detection (I8)
|
86% |
1500
17.8 IPS |
|
Depth Estimation (F32)
|
100% |
591
4.58 IPS |
|
Depth Estimation (F16)
|
100% |
585
4.54 IPS |
|
Depth Estimation (I8)
|
95% |
1727
13.4 IPS |
|
Style Transfer (F32)
|
100% |
958
1.26 IPS |
|
Style Transfer (F16)
|
100% |
957
1.26 IPS |
|
Style Transfer (I8)
|
98% |
2409
3.17 IPS |
|
Image Super-Resolution (F32)
|
100% |
330
11.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
334
11.9 IPS |
|
Image Super-Resolution (I8)
|
98% |
1189
42.5 IPS |
|
Text Classification (F32)
|
100% |
415
596.1 IPS |
|
Text Classification (F16)
|
100% |
431
619.1 IPS |
|
Text Classification (I8)
|
92% |
661
949.7 IPS |
|
Machine Translation (F32)
|
100% |
656
12.1 IPS |
|
Machine Translation (F16)
|
100% |
646
11.9 IPS |
|
Machine Translation (I8)
|
64% |
702
12.9 IPS |