Upload Date | April 14 2025 12:05 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | ZONKO D105_EEA |
Model ID | ZONKO D105_EEA |
Motherboard | exdroid |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3333 revision 0 |
Base Frequency | 1.42 GHz |
Cluster 1 | 4 Cores @ 1.42 GHz |
Cluster 2 | 4 Cores @ 1.80 GHz |
Memory Information | |
---|---|
Size | 2.72 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
123
22.9 IPS |
|
Image Classification (HP)
|
100% |
121
22.5 IPS |
|
Image Classification (Q)
|
100% |
390
72.5 IPS |
|
Image Segmentation (SP)
|
100% |
170
2.75 IPS |
|
Image Segmentation (HP)
|
100% |
172
2.79 IPS |
|
Image Segmentation (Q)
|
98% |
485
7.89 IPS |
|
Pose Estimation (SP)
|
100% |
574
0.67 IPS |
|
Pose Estimation (HP)
|
100% |
569
0.66 IPS |
|
Pose Estimation (Q)
|
84% |
1194
1.42 IPS |
|
Object Detection (SP)
|
100% |
132
10.5 IPS |
|
Object Detection (HP)
|
100% |
131
10.4 IPS |
|
Object Detection (Q)
|
83% |
356
28.8 IPS |
|
Face Detection (SP)
|
100% |
299
3.55 IPS |
|
Face Detection (HP)
|
100% |
301
3.58 IPS |
|
Face Detection (Q)
|
95% |
825
9.84 IPS |
|
Depth Estimation (SP)
|
100% |
404
3.12 IPS |
|
Depth Estimation (HP)
|
99% |
395
3.04 IPS |
|
Depth Estimation (Q)
|
64% |
993
9.10 IPS |
|
Style Transfer (SP)
|
89% |
1166
1.51 IPS |
|
Style Transfer (HP)
|
89% |
1170
1.52 IPS |
|
Style Transfer (Q)
|
98% |
2201
2.84 IPS |
|
Image Super-Resolution (SP)
|
100% |
203
7.49 IPS |
|
Image Super-Resolution (HP)
|
100% |
211
7.81 IPS |
|
Image Super-Resolution (Q)
|
97% |
601
22.3 IPS |
|
Text Classification (SP)
|
100% |
142
189.8 IPS |
|
Text Classification (HP)
|
100% |
138
183.8 IPS |
|
Text Classification (Q)
|
88% |
131
176.5 IPS |
|
Machine Translation (SP)
|
100% |
194
3.34 IPS |
|
Machine Translation (HP)
|
100% |
193
3.32 IPS |
|
Machine Translation (Q)
|
50% |
75
2.68 IPS |