Upload Date | August 27 2024 04:03 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A256B |
Model ID | samsung SM-A256B |
Motherboard | s5e8825 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.26 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
119
22.3 IPS |
|
Image Classification (F16)
|
100% |
119
22.2 IPS |
|
Image Classification (I8)
|
97% |
321
60.1 IPS |
|
Image Segmentation (F32)
|
100% |
192
3.20 IPS |
|
Image Segmentation (F16)
|
100% |
248
4.15 IPS |
|
Image Segmentation (I8)
|
98% |
361
6.03 IPS |
|
Pose Estimation (F32)
|
100% |
665
0.81 IPS |
|
Pose Estimation (F16)
|
100% |
2343
2.84 IPS |
|
Pose Estimation (I8)
|
100% |
809
0.98 IPS |
|
Object Detection (F32)
|
100% |
126
9.38 IPS |
|
Object Detection (F16)
|
100% |
126
9.38 IPS |
|
Object Detection (I8)
|
61% |
355
26.5 IPS |
|
Face Detection (F32)
|
100% |
305
3.63 IPS |
|
Face Detection (F16)
|
100% |
308
3.66 IPS |
|
Face Detection (I8)
|
86% |
704
8.37 IPS |
|
Depth Estimation (F32)
|
100% |
254
1.97 IPS |
|
Depth Estimation (F16)
|
100% |
249
1.93 IPS |
|
Depth Estimation (I8)
|
95% |
752
5.83 IPS |
|
Style Transfer (F32)
|
100% |
550
0.72 IPS |
|
Style Transfer (F16)
|
100% |
575
0.76 IPS |
|
Style Transfer (I8)
|
98% |
378
0.50 IPS |
|
Image Super-Resolution (F32)
|
100% |
258
9.21 IPS |
|
Image Super-Resolution (F16)
|
100% |
377
13.4 IPS |
|
Image Super-Resolution (I8)
|
98% |
454
16.2 IPS |
|
Text Classification (F32)
|
100% |
70
100.5 IPS |
|
Text Classification (F16)
|
100% |
84
120.9 IPS |
|
Text Classification (I8)
|
92% |
52
75.1 IPS |
|
Machine Translation (F32)
|
100% |
290
5.33 IPS |
|
Machine Translation (F16)
|
100% |
289
5.32 IPS |
|
Machine Translation (I8)
|
64% |
385
7.08 IPS |