Upload Date | January 07 2025 05:20 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | motorola moto g34 5G |
Model ID | motorola moto g34 5G |
Motherboard | fogos |
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 | 3.39 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
226
42.1 IPS |
|
Image Classification (HP)
|
100% |
226
42.1 IPS |
|
Image Classification (Q)
|
100% |
673
125.2 IPS |
|
Image Segmentation (SP)
|
100% |
288
4.66 IPS |
|
Image Segmentation (HP)
|
100% |
288
4.66 IPS |
|
Image Segmentation (Q)
|
98% |
776
12.6 IPS |
|
Pose Estimation (SP)
|
100% |
1088
1.27 IPS |
|
Pose Estimation (HP)
|
100% |
1120
1.31 IPS |
|
Pose Estimation (Q)
|
84% |
1671
1.98 IPS |
|
Object Detection (SP)
|
100% |
229
18.1 IPS |
|
Object Detection (HP)
|
100% |
226
17.9 IPS |
|
Object Detection (Q)
|
83% |
662
53.5 IPS |
|
Face Detection (SP)
|
100% |
715
8.50 IPS |
|
Face Detection (HP)
|
100% |
705
8.38 IPS |
|
Face Detection (Q)
|
95% |
1619
19.3 IPS |
|
Depth Estimation (SP)
|
100% |
948
7.31 IPS |
|
Depth Estimation (HP)
|
99% |
942
7.26 IPS |
|
Depth Estimation (Q)
|
64% |
1541
14.1 IPS |
|
Style Transfer (SP)
|
89% |
1918
2.49 IPS |
|
Style Transfer (HP)
|
89% |
1927
2.50 IPS |
|
Style Transfer (Q)
|
98% |
4009
5.17 IPS |
|
Image Super-Resolution (SP)
|
100% |
499
18.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
496
18.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
967
35.8 IPS |
|
Text Classification (SP)
|
100% |
271
362.2 IPS |
|
Text Classification (HP)
|
100% |
267
356.5 IPS |
|
Text Classification (Q)
|
88% |
501
676.2 IPS |
|
Machine Translation (SP)
|
100% |
453
7.80 IPS |
|
Machine Translation (HP)
|
100% |
454
7.81 IPS |
|
Machine Translation (Q)
|
50% |
327
11.6 IPS |