Upload Date | November 09 2024 05:44 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | motorola moto g(30) |
Model ID | motorola moto g(30) |
Motherboard | caprip |
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 @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.02 GHz |
Memory Information | |
---|---|
Size | 5.60 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
28
5.17 IPS |
|
Image Classification (HP)
|
100% |
58
10.7 IPS |
|
Image Classification (Q)
|
97% |
59
11.0 IPS |
|
Image Segmentation (SP)
|
100% |
27
0.43 IPS |
|
Image Segmentation (HP)
|
100% |
89
1.44 IPS |
|
Image Segmentation (Q)
|
98% |
89
1.45 IPS |
|
Pose Estimation (SP)
|
100% |
49
0.06 IPS |
|
Pose Estimation (HP)
|
100% |
98
0.11 IPS |
|
Pose Estimation (Q)
|
95% |
97
0.11 IPS |
|
Object Detection (SP)
|
100% |
28
2.23 IPS |
|
Object Detection (HP)
|
100% |
47
3.77 IPS |
|
Object Detection (Q)
|
89% |
47
3.77 IPS |
|
Face Detection (SP)
|
100% |
69
0.82 IPS |
|
Face Detection (HP)
|
100% |
174
2.07 IPS |
|
Face Detection (Q)
|
97% |
180
2.15 IPS |
|
Depth Estimation (SP)
|
100% |
65
0.50 IPS |
|
Depth Estimation (HP)
|
99% |
136
1.05 IPS |
|
Depth Estimation (Q)
|
62% |
111
1.06 IPS |
|
Style Transfer (SP)
|
0
|
||
Style Transfer (HP)
|
100% |
257
0.33 IPS |
|
Style Transfer (Q)
|
98% |
255
0.33 IPS |
|
Image Super-Resolution (SP)
|
100% |
32
1.17 IPS |
|
Image Super-Resolution (HP)
|
100% |
69
2.53 IPS |
|
Image Super-Resolution (Q)
|
97% |
68
2.53 IPS |
|
Text Classification (SP)
|
100% |
59
79.3 IPS |
|
Text Classification (HP)
|
100% |
59
79.2 IPS |
|
Text Classification (Q)
|
91% |
76
101.8 IPS |
|
Machine Translation (SP)
|
100% |
105
1.81 IPS |
|
Machine Translation (HP)
|
100% |
107
1.84 IPS |
|
Machine Translation (Q)
|
57% |
74
1.80 IPS |