Upload Date | September 18 2024 10:02 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% |
140
26.1 IPS |
|
Image Classification (HP)
|
100% |
150
27.9 IPS |
|
Image Classification (Q)
|
100% |
337
62.7 IPS |
|
Image Segmentation (SP)
|
100% |
177
2.87 IPS |
|
Image Segmentation (HP)
|
100% |
178
2.88 IPS |
|
Image Segmentation (Q)
|
98% |
449
7.31 IPS |
|
Pose Estimation (SP)
|
100% |
793
0.93 IPS |
|
Pose Estimation (HP)
|
100% |
770
0.90 IPS |
|
Pose Estimation (Q)
|
84% |
989
1.17 IPS |
|
Object Detection (SP)
|
100% |
159
12.6 IPS |
|
Object Detection (HP)
|
100% |
168
13.4 IPS |
|
Object Detection (Q)
|
83% |
381
30.8 IPS |
|
Face Detection (SP)
|
100% |
413
4.91 IPS |
|
Face Detection (HP)
|
100% |
441
5.24 IPS |
|
Face Detection (Q)
|
95% |
1040
12.4 IPS |
|
Depth Estimation (SP)
|
100% |
563
4.34 IPS |
|
Depth Estimation (HP)
|
99% |
570
4.39 IPS |
|
Depth Estimation (Q)
|
64% |
931
8.53 IPS |
|
Style Transfer (SP)
|
89% |
1355
1.76 IPS |
|
Style Transfer (HP)
|
89% |
1264
1.64 IPS |
|
Style Transfer (Q)
|
98% |
2250
2.90 IPS |
|
Image Super-Resolution (SP)
|
100% |
307
11.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
292
10.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
527
19.5 IPS |
|
Text Classification (SP)
|
100% |
141
187.9 IPS |
|
Text Classification (HP)
|
100% |
146
194.3 IPS |
|
Text Classification (Q)
|
88% |
262
353.0 IPS |
|
Machine Translation (SP)
|
100% |
242
4.17 IPS |
|
Machine Translation (HP)
|
100% |
220
3.78 IPS |
|
Machine Translation (Q)
|
50% |
121
4.30 IPS |