Upload Date | September 17 2024 07:39 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | asus Zenfone 5Z |
Model ID | asus Zenfone 5Z |
Motherboard | sdm845 |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 6 part 2050 revision 13 |
Base Frequency | 1.77 GHz |
Cluster 1 | 4 Cores @ 1.77 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 7.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
221
41.1 IPS |
|
Image Classification (HP)
|
100% |
314
58.3 IPS |
|
Image Classification (Q)
|
97% |
317
59.2 IPS |
|
Image Segmentation (SP)
|
100% |
282
4.56 IPS |
|
Image Segmentation (HP)
|
100% |
388
6.29 IPS |
|
Image Segmentation (Q)
|
98% |
385
6.26 IPS |
|
Pose Estimation (SP)
|
100% |
431
0.50 IPS |
|
Pose Estimation (HP)
|
100% |
670
0.78 IPS |
|
Pose Estimation (Q)
|
95% |
666
0.78 IPS |
|
Object Detection (SP)
|
100% |
117
9.28 IPS |
|
Object Detection (HP)
|
100% |
183
14.5 IPS |
|
Object Detection (Q)
|
89% |
210
16.8 IPS |
|
Face Detection (SP)
|
100% |
609
7.23 IPS |
|
Face Detection (HP)
|
100% |
757
9.00 IPS |
|
Face Detection (Q)
|
97% |
783
9.34 IPS |
|
Depth Estimation (SP)
|
100% |
563
4.33 IPS |
|
Depth Estimation (HP)
|
99% |
805
6.22 IPS |
|
Depth Estimation (Q)
|
62% |
654
6.19 IPS |
|
Style Transfer (SP)
|
100% |
1254
1.61 IPS |
|
Style Transfer (HP)
|
100% |
1816
2.34 IPS |
|
Style Transfer (Q)
|
98% |
1817
2.34 IPS |
|
Image Super-Resolution (SP)
|
100% |
269
9.92 IPS |
|
Image Super-Resolution (HP)
|
100% |
418
15.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
410
15.2 IPS |
|
Text Classification (SP)
|
100% |
82
110.1 IPS |
|
Text Classification (HP)
|
100% |
82
109.8 IPS |
|
Text Classification (Q)
|
91% |
97
130.1 IPS |
|
Machine Translation (SP)
|
100% |
146
2.51 IPS |
|
Machine Translation (HP)
|
100% |
148
2.54 IPS |
|
Machine Translation (Q)
|
57% |
116
2.83 IPS |