Upload Date | November 24 2024 08:53 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm Snapdragon 720G |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy A72 |
Model ID | samsung SM-A725F |
Motherboard | atoll |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 15 part 2052 revision 15 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.32 GHz |
Memory Information | |
---|---|
Size | 5.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
84
15.5 IPS |
|
Image Classification (HP)
|
100% |
84
15.6 IPS |
|
Image Classification (Q)
|
99% |
192
35.8 IPS |
|
Image Segmentation (SP)
|
100% |
114
1.84 IPS |
|
Image Segmentation (HP)
|
100% |
115
1.86 IPS |
|
Image Segmentation (Q)
|
98% |
202
3.28 IPS |
|
Pose Estimation (SP)
|
100% |
153
0.18 IPS |
|
Pose Estimation (HP)
|
100% |
154
0.18 IPS |
|
Pose Estimation (Q)
|
98% |
574
0.67 IPS |
|
Object Detection (SP)
|
100% |
84
6.63 IPS |
|
Object Detection (HP)
|
100% |
84
6.68 IPS |
|
Object Detection (Q)
|
87% |
212
17.0 IPS |
|
Face Detection (SP)
|
100% |
214
2.55 IPS |
|
Face Detection (HP)
|
100% |
216
2.57 IPS |
|
Face Detection (Q)
|
97% |
410
4.89 IPS |
|
Depth Estimation (SP)
|
100% |
182
1.41 IPS |
|
Depth Estimation (HP)
|
99% |
183
1.41 IPS |
|
Depth Estimation (Q)
|
64% |
408
3.71 IPS |
|
Style Transfer (SP)
|
100% |
308
0.40 IPS |
|
Style Transfer (HP)
|
100% |
307
0.40 IPS |
|
Style Transfer (Q)
|
98% |
909
1.17 IPS |
|
Image Super-Resolution (SP)
|
100% |
91
3.36 IPS |
|
Image Super-Resolution (HP)
|
100% |
91
3.37 IPS |
|
Image Super-Resolution (Q)
|
97% |
296
11.0 IPS |
|
Text Classification (SP)
|
100% |
118
157.4 IPS |
|
Text Classification (HP)
|
100% |
115
153.9 IPS |
|
Text Classification (Q)
|
91% |
192
258.5 IPS |
|
Machine Translation (SP)
|
100% |
205
3.52 IPS |
|
Machine Translation (HP)
|
100% |
209
3.60 IPS |
|
Machine Translation (Q)
|
57% |
151
3.68 IPS |