Upload Date | December 13 2024 10:31 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM Unisoc |
System Information | |
---|---|
Operating System | Android 13 |
Model | ZTE ZTE Blade A54 |
Model ID | ZTE ZTE Blade A54 |
Motherboard | s9863a1h10 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Unisoc |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3333 revision 0 |
Base Frequency | 1.20 GHz |
Cluster 1 | 4 Cores @ 1.20 GHz |
Cluster 2 | 4 Cores @ 1.60 GHz |
Memory Information | |
---|---|
Size | 3.77 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
120
22.2 IPS |
|
Image Classification (HP)
|
100% |
119
22.1 IPS |
|
Image Classification (Q)
|
100% |
307
57.2 IPS |
|
Image Segmentation (SP)
|
100% |
159
2.58 IPS |
|
Image Segmentation (HP)
|
100% |
167
2.70 IPS |
|
Image Segmentation (Q)
|
98% |
444
7.22 IPS |
|
Pose Estimation (SP)
|
100% |
555
0.65 IPS |
|
Pose Estimation (HP)
|
100% |
572
0.67 IPS |
|
Pose Estimation (Q)
|
84% |
1158
1.37 IPS |
|
Object Detection (SP)
|
100% |
119
9.42 IPS |
|
Object Detection (HP)
|
100% |
119
9.42 IPS |
|
Object Detection (Q)
|
83% |
324
26.2 IPS |
|
Face Detection (SP)
|
100% |
307
3.64 IPS |
|
Face Detection (HP)
|
100% |
315
3.74 IPS |
|
Face Detection (Q)
|
95% |
756
9.03 IPS |
|
Depth Estimation (SP)
|
100% |
394
3.04 IPS |
|
Depth Estimation (HP)
|
99% |
411
3.17 IPS |
|
Depth Estimation (Q)
|
64% |
878
8.04 IPS |
|
Style Transfer (SP)
|
89% |
1191
1.55 IPS |
|
Style Transfer (HP)
|
89% |
1224
1.59 IPS |
|
Style Transfer (Q)
|
98% |
2317
2.99 IPS |
|
Image Super-Resolution (SP)
|
100% |
183
6.74 IPS |
|
Image Super-Resolution (HP)
|
100% |
186
6.88 IPS |
|
Image Super-Resolution (Q)
|
97% |
584
21.7 IPS |
|
Text Classification (SP)
|
100% |
107
143.0 IPS |
|
Text Classification (HP)
|
100% |
108
144.6 IPS |
|
Text Classification (Q)
|
88% |
144
194.4 IPS |
|
Machine Translation (SP)
|
100% |
181
3.12 IPS |
|
Machine Translation (HP)
|
100% |
183
3.16 IPS |
|
Machine Translation (Q)
|
50% |
94
3.35 IPS |