User | Farzad |
Upload Date | February 20 2025 02:34 AM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
168
31.2 IPS |
|
Image Classification (HP)
|
100% |
306
56.9 IPS |
|
Image Classification (Q)
|
99% |
292
54.5 IPS |
|
Image Segmentation (SP)
|
100% |
237
3.85 IPS |
|
Image Segmentation (HP)
|
100% |
394
6.39 IPS |
|
Image Segmentation (Q)
|
98% |
385
6.26 IPS |
|
Pose Estimation (SP)
|
100% |
153
0.18 IPS |
|
Pose Estimation (HP)
|
100% |
180
0.21 IPS |
|
Pose Estimation (Q)
|
96% |
179
0.21 IPS |
|
Object Detection (SP)
|
100% |
143
11.3 IPS |
|
Object Detection (HP)
|
100% |
238
18.9 IPS |
|
Object Detection (Q)
|
83% |
232
18.8 IPS |
|
Face Detection (SP)
|
100% |
558
6.63 IPS |
|
Face Detection (HP)
|
100% |
832
9.88 IPS |
|
Face Detection (Q)
|
97% |
777
9.27 IPS |
|
Depth Estimation (SP)
|
100% |
296
2.28 IPS |
|
Depth Estimation (HP)
|
99% |
381
2.93 IPS |
|
Depth Estimation (Q)
|
62% |
309
2.92 IPS |
|
Style Transfer (SP)
|
100% |
597
0.77 IPS |
|
Style Transfer (HP)
|
100% |
842
1.08 IPS |
|
Style Transfer (Q)
|
98% |
839
1.08 IPS |
|
Image Super-Resolution (SP)
|
100% |
159
5.88 IPS |
|
Image Super-Resolution (HP)
|
100% |
246
9.08 IPS |
|
Image Super-Resolution (Q)
|
97% |
243
9.00 IPS |
|
Text Classification (SP)
|
100% |
170
226.8 IPS |
|
Text Classification (HP)
|
100% |
169
226.1 IPS |
|
Text Classification (Q)
|
91% |
334
448.4 IPS |
|
Machine Translation (SP)
|
100% |
280
4.83 IPS |
|
Machine Translation (HP)
|
100% |
285
4.91 IPS |
|
Machine Translation (Q)
|
57% |
280
6.84 IPS |