Upload Date | June 25 2025 04:27 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 25040RP0AG |
Model ID | Xiaomi 25040RP0AG |
Motherboard | taiko |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.20 GHz |
Memory Information | |
---|---|
Size | 7.64 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
223
41.4 IPS |
|
Image Classification (HP)
|
100% |
224
41.7 IPS |
|
Image Classification (Q)
|
100% |
641
119.2 IPS |
|
Image Segmentation (SP)
|
100% |
279
4.53 IPS |
|
Image Segmentation (HP)
|
100% |
278
4.51 IPS |
|
Image Segmentation (Q)
|
98% |
708
11.5 IPS |
|
Pose Estimation (SP)
|
100% |
1094
1.28 IPS |
|
Pose Estimation (HP)
|
100% |
1079
1.26 IPS |
|
Pose Estimation (Q)
|
84% |
1593
1.89 IPS |
|
Object Detection (SP)
|
100% |
225
17.8 IPS |
|
Object Detection (HP)
|
100% |
226
17.9 IPS |
|
Object Detection (Q)
|
83% |
629
50.8 IPS |
|
Face Detection (SP)
|
100% |
715
8.49 IPS |
|
Face Detection (HP)
|
100% |
716
8.51 IPS |
|
Face Detection (Q)
|
95% |
1460
17.4 IPS |
|
Depth Estimation (SP)
|
100% |
901
6.94 IPS |
|
Depth Estimation (HP)
|
99% |
641
4.94 IPS |
|
Depth Estimation (Q)
|
64% |
1470
13.5 IPS |
|
Style Transfer (SP)
|
89% |
1760
2.28 IPS |
|
Style Transfer (HP)
|
89% |
1740
2.26 IPS |
|
Style Transfer (Q)
|
98% |
3680
4.75 IPS |
|
Image Super-Resolution (SP)
|
100% |
393
14.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
453
16.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
884
32.8 IPS |
|
Text Classification (SP)
|
100% |
274
365.9 IPS |
|
Text Classification (HP)
|
100% |
272
362.9 IPS |
|
Text Classification (Q)
|
88% |
485
654.6 IPS |
|
Machine Translation (SP)
|
100% |
469
8.09 IPS |
|
Machine Translation (HP)
|
100% |
462
7.96 IPS |
|
Machine Translation (Q)
|
50% |
329
11.7 IPS |