User | xRoach |
Upload Date | January 11 2025 10:16 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
78
14.4 IPS |
|
Image Classification (HP)
|
100% |
113
20.9 IPS |
|
Image Classification (Q)
|
99% |
108
20.1 IPS |
|
Image Segmentation (SP)
|
100% |
113
1.83 IPS |
|
Image Segmentation (HP)
|
100% |
169
2.73 IPS |
|
Image Segmentation (Q)
|
98% |
164
2.67 IPS |
|
Pose Estimation (SP)
|
100% |
52
0.06 IPS |
|
Pose Estimation (HP)
|
100% |
70
0.08 IPS |
|
Pose Estimation (Q)
|
96% |
69
0.08 IPS |
|
Object Detection (SP)
|
100% |
62
4.91 IPS |
|
Object Detection (HP)
|
100% |
92
7.30 IPS |
|
Object Detection (Q)
|
83% |
91
7.39 IPS |
|
Face Detection (SP)
|
100% |
242
2.88 IPS |
|
Face Detection (HP)
|
100% |
337
4.01 IPS |
|
Face Detection (Q)
|
97% |
315
3.76 IPS |
|
Depth Estimation (SP)
|
100% |
116
0.89 IPS |
|
Depth Estimation (HP)
|
99% |
163
1.26 IPS |
|
Depth Estimation (Q)
|
62% |
119
1.13 IPS |
|
Style Transfer (SP)
|
100% |
209
0.27 IPS |
|
Style Transfer (HP)
|
100% |
320
0.41 IPS |
|
Style Transfer (Q)
|
98% |
317
0.41 IPS |
|
Image Super-Resolution (SP)
|
100% |
63
2.33 IPS |
|
Image Super-Resolution (HP)
|
100% |
88
3.25 IPS |
|
Image Super-Resolution (Q)
|
97% |
87
3.23 IPS |
|
Text Classification (SP)
|
100% |
71
94.7 IPS |
|
Text Classification (HP)
|
100% |
71
95.1 IPS |
|
Text Classification (Q)
|
91% |
104
139.6 IPS |
|
Machine Translation (SP)
|
100% |
119
2.05 IPS |
|
Machine Translation (HP)
|
100% |
118
2.04 IPS |
|
Machine Translation (Q)
|
57% |
96
2.35 IPS |