Upload Date | September 12 2024 09:40 AM |
Views | 22 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2409BRN2CA |
Model ID | Xiaomi 2409BRN2CA |
Motherboard | pond |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.70 GHz |
Cluster 1 | 6 Cores @ 1.70 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 3.60 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
101
18.7 IPS |
|
Image Classification (HP)
|
100% |
101
18.7 IPS |
|
Image Classification (Q)
|
100% |
201
37.4 IPS |
|
Image Segmentation (SP)
|
100% |
117
1.89 IPS |
|
Image Segmentation (HP)
|
100% |
116
1.88 IPS |
|
Image Segmentation (Q)
|
98% |
255
4.15 IPS |
|
Pose Estimation (SP)
|
100% |
456
0.53 IPS |
|
Pose Estimation (HP)
|
100% |
456
0.53 IPS |
|
Pose Estimation (Q)
|
84% |
406
0.48 IPS |
|
Object Detection (SP)
|
100% |
93
7.35 IPS |
|
Object Detection (HP)
|
100% |
91
7.23 IPS |
|
Object Detection (Q)
|
83% |
198
16.0 IPS |
|
Face Detection (SP)
|
100% |
306
3.64 IPS |
|
Face Detection (HP)
|
100% |
302
3.59 IPS |
|
Face Detection (Q)
|
95% |
539
6.44 IPS |
|
Depth Estimation (SP)
|
100% |
378
2.92 IPS |
|
Depth Estimation (HP)
|
99% |
381
2.94 IPS |
|
Depth Estimation (Q)
|
64% |
438
4.01 IPS |
|
Style Transfer (SP)
|
89% |
766
0.99 IPS |
|
Style Transfer (HP)
|
89% |
761
0.99 IPS |
|
Style Transfer (Q)
|
98% |
1018
1.31 IPS |
|
Image Super-Resolution (SP)
|
100% |
190
7.02 IPS |
|
Image Super-Resolution (HP)
|
100% |
198
7.33 IPS |
|
Image Super-Resolution (Q)
|
97% |
241
8.94 IPS |
|
Text Classification (SP)
|
100% |
110
146.5 IPS |
|
Text Classification (HP)
|
100% |
109
146.0 IPS |
|
Text Classification (Q)
|
88% |
181
244.7 IPS |
|
Machine Translation (SP)
|
100% |
215
3.70 IPS |
|
Machine Translation (HP)
|
100% |
213
3.66 IPS |
|
Machine Translation (Q)
|
50% |
142
5.03 IPS |