Upload Date | August 18 2024 11:17 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A556E |
Model ID | samsung SM-A556E |
Motherboard | s5e8845 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 2.05 GHz |
Cluster 1 | 4 Cores @ 2.05 GHz |
Cluster 2 | 4 Cores @ 2.75 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
91
17.0 IPS |
|
Image Classification (F16)
|
100% |
91
17.0 IPS |
|
Image Classification (I8)
|
97% |
288
53.9 IPS |
|
Image Segmentation (F32)
|
100% |
253
4.22 IPS |
|
Image Segmentation (F16)
|
100% |
329
5.50 IPS |
|
Image Segmentation (I8)
|
98% |
331
5.53 IPS |
|
Pose Estimation (F32)
|
0
|
||
Pose Estimation (F16)
|
0
|
||
Pose Estimation (I8)
|
100% |
601
0.73 IPS |
|
Object Detection (F32)
|
100% |
95
7.08 IPS |
|
Object Detection (F16)
|
100% |
95
7.11 IPS |
|
Object Detection (I8)
|
61% |
309
23.1 IPS |
|
Face Detection (F32)
|
100% |
261
3.11 IPS |
|
Face Detection (F16)
|
100% |
262
3.12 IPS |
|
Face Detection (I8)
|
86% |
692
8.23 IPS |
|
Depth Estimation (F32)
|
100% |
207
1.61 IPS |
|
Depth Estimation (F16)
|
100% |
207
1.60 IPS |
|
Depth Estimation (I8)
|
95% |
682
5.29 IPS |
|
Style Transfer (F32)
|
100% |
366
0.48 IPS |
|
Style Transfer (F16)
|
100% |
368
0.48 IPS |
|
Style Transfer (I8)
|
98% |
1138
1.50 IPS |
|
Image Super-Resolution (F32)
|
100% |
558
19.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
515
18.4 IPS |
|
Image Super-Resolution (I8)
|
98% |
391
14.0 IPS |
|
Text Classification (F32)
|
100% |
119
171.2 IPS |
|
Text Classification (F16)
|
100% |
119
171.5 IPS |
|
Text Classification (I8)
|
92% |
295
424.0 IPS |
|
Machine Translation (F32)
|
100% |
226
4.16 IPS |
|
Machine Translation (F16)
|
100% |
225
4.15 IPS |
|
Machine Translation (I8)
|
64% |
388
7.14 IPS |