Upload Date | September 19 2024 12:48 PM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 13 |
Model | motorola moto g82 5G |
Model ID | motorola moto g82 5G |
Motherboard | rhodep |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.32 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
106
19.8 IPS |
|
Image Classification (HP)
|
100% |
182
33.9 IPS |
|
Image Classification (Q)
|
97% |
194
36.1 IPS |
|
Image Segmentation (SP)
|
100% |
151
2.46 IPS |
|
Image Segmentation (HP)
|
100% |
276
4.48 IPS |
|
Image Segmentation (Q)
|
98% |
273
4.44 IPS |
|
Pose Estimation (SP)
|
100% |
216
0.25 IPS |
|
Pose Estimation (HP)
|
100% |
279
0.33 IPS |
|
Pose Estimation (Q)
|
95% |
278
0.33 IPS |
|
Object Detection (SP)
|
100% |
95
7.54 IPS |
|
Object Detection (HP)
|
100% |
148
11.8 IPS |
|
Object Detection (Q)
|
89% |
163
13.0 IPS |
|
Face Detection (SP)
|
100% |
266
3.16 IPS |
|
Face Detection (HP)
|
100% |
496
5.89 IPS |
|
Face Detection (Q)
|
97% |
509
6.07 IPS |
|
Depth Estimation (SP)
|
100% |
252
1.95 IPS |
|
Depth Estimation (HP)
|
99% |
426
3.29 IPS |
|
Depth Estimation (Q)
|
62% |
350
3.32 IPS |
|
Style Transfer (SP)
|
100% |
492
0.63 IPS |
|
Style Transfer (HP)
|
100% |
1063
1.37 IPS |
|
Style Transfer (Q)
|
98% |
1059
1.37 IPS |
|
Image Super-Resolution (SP)
|
100% |
130
4.79 IPS |
|
Image Super-Resolution (HP)
|
100% |
222
8.20 IPS |
|
Image Super-Resolution (Q)
|
97% |
219
8.12 IPS |
|
Text Classification (SP)
|
100% |
113
151.3 IPS |
|
Text Classification (HP)
|
100% |
113
151.1 IPS |
|
Text Classification (Q)
|
91% |
211
283.3 IPS |
|
Machine Translation (SP)
|
100% |
200
3.44 IPS |
|
Machine Translation (HP)
|
100% |
200
3.44 IPS |
|
Machine Translation (Q)
|
57% |
160
3.91 IPS |