Upload Date | March 31 2025 01:21 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM UNISOC |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X200 |
Model ID | samsung SM-X200 |
Motherboard | ums512_25c10 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM UNISOC |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 8 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 2.42 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
196
36.4 IPS |
|
Image Classification (HP)
|
100% |
179
33.3 IPS |
|
Image Classification (Q)
|
100% |
504
93.7 IPS |
|
Image Segmentation (SP)
|
100% |
236
3.83 IPS |
|
Image Segmentation (HP)
|
100% |
206
3.33 IPS |
|
Image Segmentation (Q)
|
98% |
637
10.4 IPS |
|
Pose Estimation (SP)
|
100% |
662
0.77 IPS |
|
Pose Estimation (HP)
|
100% |
673
0.79 IPS |
|
Pose Estimation (Q)
|
84% |
714
0.85 IPS |
|
Object Detection (SP)
|
100% |
155
12.3 IPS |
|
Object Detection (HP)
|
100% |
182
14.4 IPS |
|
Object Detection (Q)
|
83% |
423
34.2 IPS |
|
Face Detection (SP)
|
100% |
466
5.54 IPS |
|
Face Detection (HP)
|
100% |
488
5.80 IPS |
|
Face Detection (Q)
|
95% |
1189
14.2 IPS |
|
Depth Estimation (SP)
|
100% |
513
3.95 IPS |
|
Depth Estimation (HP)
|
99% |
636
4.90 IPS |
|
Depth Estimation (Q)
|
64% |
1062
9.73 IPS |
|
Style Transfer (SP)
|
89% |
1522
1.98 IPS |
|
Style Transfer (HP)
|
89% |
1390
1.80 IPS |
|
Style Transfer (Q)
|
98% |
2307
2.97 IPS |
|
Image Super-Resolution (SP)
|
100% |
316
11.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
335
12.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
643
23.8 IPS |
|
Text Classification (SP)
|
100% |
184
245.3 IPS |
|
Text Classification (HP)
|
100% |
171
227.7 IPS |
|
Text Classification (Q)
|
88% |
245
330.0 IPS |
|
Machine Translation (SP)
|
100% |
210
3.62 IPS |
|
Machine Translation (HP)
|
100% |
233
4.02 IPS |
|
Machine Translation (Q)
|
50% |
121
4.29 IPS |