Upload Date | November 19 2024 11:04 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 23129RAA4G |
Model ID | Xiaomi 23129RAA4G |
Motherboard | bengal |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3337 revision 0 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores @ 1.90 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 7.42 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
154
28.5 IPS |
|
Image Classification (HP)
|
100% |
163
30.3 IPS |
|
Image Classification (Q)
|
100% |
314
58.3 IPS |
|
Image Segmentation (SP)
|
100% |
214
3.47 IPS |
|
Image Segmentation (HP)
|
100% |
211
3.42 IPS |
|
Image Segmentation (Q)
|
98% |
397
6.45 IPS |
|
Pose Estimation (SP)
|
100% |
812
0.95 IPS |
|
Pose Estimation (HP)
|
100% |
799
0.93 IPS |
|
Pose Estimation (Q)
|
84% |
690
0.82 IPS |
|
Object Detection (SP)
|
100% |
165
13.1 IPS |
|
Object Detection (HP)
|
100% |
166
13.2 IPS |
|
Object Detection (Q)
|
83% |
313
25.3 IPS |
|
Face Detection (SP)
|
100% |
449
5.34 IPS |
|
Face Detection (HP)
|
100% |
463
5.50 IPS |
|
Face Detection (Q)
|
95% |
732
8.74 IPS |
|
Depth Estimation (SP)
|
100% |
659
5.07 IPS |
|
Depth Estimation (HP)
|
99% |
664
5.11 IPS |
|
Depth Estimation (Q)
|
64% |
714
6.54 IPS |
|
Style Transfer (SP)
|
89% |
1431
1.86 IPS |
|
Style Transfer (HP)
|
89% |
1424
1.85 IPS |
|
Style Transfer (Q)
|
98% |
1720
2.22 IPS |
|
Image Super-Resolution (SP)
|
100% |
357
13.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
353
13.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
411
15.2 IPS |
|
Text Classification (SP)
|
100% |
196
262.0 IPS |
|
Text Classification (HP)
|
100% |
196
262.2 IPS |
|
Text Classification (Q)
|
88% |
293
395.3 IPS |
|
Machine Translation (SP)
|
100% |
319
5.50 IPS |
|
Machine Translation (HP)
|
100% |
312
5.38 IPS |
|
Machine Translation (Q)
|
50% |
174
6.18 IPS |