Upload Date | November 20 2024 06:31 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 460 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Nokia 3.4 |
Model ID | HMD Global Nokia 3.4 |
Motherboard | DoctorStrange |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.61 GHz |
Cluster 2 | 4 Cores @ 1.80 GHz |
Memory Information | |
---|---|
Size | 2.61 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
103
19.1 IPS |
|
Image Classification (HP)
|
100% |
92
17.1 IPS |
|
Image Classification (Q)
|
100% |
157
29.2 IPS |
|
Image Segmentation (SP)
|
100% |
113
1.84 IPS |
|
Image Segmentation (HP)
|
100% |
126
2.04 IPS |
|
Image Segmentation (Q)
|
98% |
221
3.59 IPS |
|
Pose Estimation (SP)
|
100% |
509
0.59 IPS |
|
Pose Estimation (HP)
|
100% |
537
0.63 IPS |
|
Pose Estimation (Q)
|
84% |
461
0.55 IPS |
|
Object Detection (SP)
|
100% |
101
8.02 IPS |
|
Object Detection (HP)
|
100% |
100
7.95 IPS |
|
Object Detection (Q)
|
83% |
188
15.2 IPS |
|
Face Detection (SP)
|
100% |
261
3.10 IPS |
|
Face Detection (HP)
|
100% |
280
3.33 IPS |
|
Face Detection (Q)
|
95% |
411
4.91 IPS |
|
Depth Estimation (SP)
|
100% |
389
3.00 IPS |
|
Depth Estimation (HP)
|
99% |
383
2.95 IPS |
|
Depth Estimation (Q)
|
64% |
328
3.01 IPS |
|
Style Transfer (SP)
|
89% |
956
1.24 IPS |
|
Style Transfer (HP)
|
89% |
822
1.07 IPS |
|
Style Transfer (Q)
|
98% |
789
1.02 IPS |
|
Image Super-Resolution (SP)
|
100% |
177
6.53 IPS |
|
Image Super-Resolution (HP)
|
100% |
178
6.58 IPS |
|
Image Super-Resolution (Q)
|
97% |
186
6.90 IPS |
|
Text Classification (SP)
|
100% |
97
128.9 IPS |
|
Text Classification (HP)
|
100% |
87
116.0 IPS |
|
Text Classification (Q)
|
88% |
108
146.3 IPS |
|
Machine Translation (SP)
|
100% |
140
2.41 IPS |
|
Machine Translation (HP)
|
100% |
136
2.34 IPS |
|
Machine Translation (Q)
|
50% |
66
2.34 IPS |