Upload Date | February 14 2025 07:55 PM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 730G |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy M51 |
Model ID | samsung SM-M515F |
Motherboard | sm6150 |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.34 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
72
13.4 IPS |
|
Image Classification (HP)
|
100% |
113
21.1 IPS |
|
Image Classification (Q)
|
97% |
126
23.4 IPS |
|
Image Segmentation (SP)
|
100% |
84
1.35 IPS |
|
Image Segmentation (HP)
|
100% |
135
2.18 IPS |
|
Image Segmentation (Q)
|
98% |
142
2.32 IPS |
|
Pose Estimation (SP)
|
100% |
152
0.18 IPS |
|
Pose Estimation (HP)
|
100% |
199
0.23 IPS |
|
Pose Estimation (Q)
|
95% |
194
0.23 IPS |
|
Object Detection (SP)
|
100% |
60
4.74 IPS |
|
Object Detection (HP)
|
100% |
87
6.90 IPS |
|
Object Detection (Q)
|
89% |
89
7.10 IPS |
|
Face Detection (SP)
|
100% |
166
1.97 IPS |
|
Face Detection (HP)
|
100% |
289
3.43 IPS |
|
Face Detection (Q)
|
97% |
310
3.70 IPS |
|
Depth Estimation (SP)
|
100% |
172
1.33 IPS |
|
Depth Estimation (HP)
|
99% |
276
2.13 IPS |
|
Depth Estimation (Q)
|
62% |
233
2.21 IPS |
|
Style Transfer (SP)
|
100% |
317
0.41 IPS |
|
Style Transfer (HP)
|
100% |
681
0.88 IPS |
|
Style Transfer (Q)
|
98% |
659
0.85 IPS |
|
Image Super-Resolution (SP)
|
100% |
85
3.13 IPS |
|
Image Super-Resolution (HP)
|
100% |
127
4.71 IPS |
|
Image Super-Resolution (Q)
|
97% |
129
4.79 IPS |
|
Text Classification (SP)
|
100% |
123
163.6 IPS |
|
Text Classification (HP)
|
100% |
122
162.4 IPS |
|
Text Classification (Q)
|
91% |
197
264.7 IPS |
|
Machine Translation (SP)
|
100% |
212
3.65 IPS |
|
Machine Translation (HP)
|
100% |
217
3.73 IPS |
|
Machine Translation (Q)
|
57% |
158
3.86 IPS |