User | benched |
Upload Date | October 08 2024 08:15 PM |
Views | 13 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM MT6769V/CZ |
System Information | |
---|---|
Operating System | Android 12 |
Model | motorola moto g31(w) |
Model ID | motorola moto g31(w) |
Motherboard | cofud |
CPU Information | |
---|---|
Name | ARM MT6769V/CZ |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 3.63 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
70
13.0 IPS |
|
Image Classification (HP)
|
100% |
117
21.8 IPS |
|
Image Classification (Q)
|
99% |
110
20.5 IPS |
|
Image Segmentation (SP)
|
100% |
105
1.70 IPS |
|
Image Segmentation (HP)
|
100% |
193
3.13 IPS |
|
Image Segmentation (Q)
|
98% |
179
2.91 IPS |
|
Pose Estimation (SP)
|
100% |
54
0.06 IPS |
|
Pose Estimation (HP)
|
100% |
81
0.09 IPS |
|
Pose Estimation (Q)
|
96% |
80
0.09 IPS |
|
Object Detection (SP)
|
100% |
59
4.66 IPS |
|
Object Detection (HP)
|
100% |
98
7.74 IPS |
|
Object Detection (Q)
|
83% |
96
7.73 IPS |
|
Face Detection (SP)
|
100% |
222
2.64 IPS |
|
Face Detection (HP)
|
100% |
344
4.09 IPS |
|
Face Detection (Q)
|
97% |
322
3.84 IPS |
|
Depth Estimation (SP)
|
100% |
121
0.93 IPS |
|
Depth Estimation (HP)
|
99% |
172
1.32 IPS |
|
Depth Estimation (Q)
|
62% |
139
1.32 IPS |
|
Style Transfer (SP)
|
100% |
242
0.31 IPS |
|
Style Transfer (HP)
|
100% |
373
0.48 IPS |
|
Style Transfer (Q)
|
98% |
371
0.48 IPS |
|
Image Super-Resolution (SP)
|
100% |
66
2.45 IPS |
|
Image Super-Resolution (HP)
|
100% |
103
3.80 IPS |
|
Image Super-Resolution (Q)
|
97% |
102
3.77 IPS |
|
Text Classification (SP)
|
100% |
68
90.9 IPS |
|
Text Classification (HP)
|
100% |
68
91.2 IPS |
|
Text Classification (Q)
|
91% |
102
137.7 IPS |
|
Machine Translation (SP)
|
100% |
121
2.09 IPS |
|
Machine Translation (HP)
|
100% |
122
2.10 IPS |
|
Machine Translation (Q)
|
57% |
92
2.25 IPS |