User | Farzad |
Upload Date | February 20 2025 02:48 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A256E |
Model ID | samsung SM-A256E |
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 |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
115
21.3 IPS |
|
Image Classification (HP)
|
100% |
116
21.6 IPS |
|
Image Classification (Q)
|
99% |
301
56.1 IPS |
|
Image Segmentation (SP)
|
100% |
172
2.78 IPS |
|
Image Segmentation (HP)
|
100% |
238
3.86 IPS |
|
Image Segmentation (Q)
|
98% |
373
6.07 IPS |
|
Pose Estimation (SP)
|
100% |
680
0.79 IPS |
|
Pose Estimation (HP)
|
100% |
2158
2.52 IPS |
|
Pose Estimation (Q)
|
98% |
839
0.98 IPS |
|
Object Detection (SP)
|
100% |
116
9.18 IPS |
|
Object Detection (HP)
|
100% |
116
9.21 IPS |
|
Object Detection (Q)
|
87% |
346
27.8 IPS |
|
Face Detection (SP)
|
100% |
301
3.58 IPS |
|
Face Detection (HP)
|
100% |
303
3.61 IPS |
|
Face Detection (Q)
|
97% |
702
8.37 IPS |
|
Depth Estimation (SP)
|
100% |
250
1.93 IPS |
|
Depth Estimation (HP)
|
99% |
251
1.93 IPS |
|
Depth Estimation (Q)
|
64% |
625
5.67 IPS |
|
Style Transfer (SP)
|
100% |
555
0.71 IPS |
|
Style Transfer (HP)
|
100% |
428
0.55 IPS |
|
Style Transfer (Q)
|
98% |
380
0.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
242
8.92 IPS |
|
Image Super-Resolution (HP)
|
100% |
335
12.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
438
16.2 IPS |
|
Text Classification (SP)
|
100% |
73
96.8 IPS |
|
Text Classification (HP)
|
100% |
169
225.0 IPS |
|
Text Classification (Q)
|
91% |
53
71.9 IPS |
|
Machine Translation (SP)
|
100% |
286
4.92 IPS |
|
Machine Translation (HP)
|
100% |
282
4.86 IPS |
|
Machine Translation (Q)
|
57% |
275
6.71 IPS |