User | mpoloton |
Upload Date | July 03 2025 01:53 PM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 24090RA29G |
Model ID | Xiaomi 24090RA29G |
Motherboard | malachite |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.50 GHz |
Memory Information | |
---|---|
Size | 7.25 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
460
85.5 IPS |
|
Image Classification (HP)
|
100% |
468
87.1 IPS |
|
Image Classification (Q)
|
100% |
1482
275.5 IPS |
|
Image Segmentation (SP)
|
100% |
538
8.73 IPS |
|
Image Segmentation (HP)
|
100% |
530
8.59 IPS |
|
Image Segmentation (Q)
|
98% |
1721
28.0 IPS |
|
Pose Estimation (SP)
|
100% |
2025
2.36 IPS |
|
Pose Estimation (HP)
|
100% |
2026
2.36 IPS |
|
Pose Estimation (Q)
|
84% |
3883
4.60 IPS |
|
Object Detection (SP)
|
100% |
460
36.5 IPS |
|
Object Detection (HP)
|
100% |
452
35.8 IPS |
|
Object Detection (Q)
|
83% |
1429
115.5 IPS |
|
Face Detection (SP)
|
100% |
1053
12.5 IPS |
|
Face Detection (HP)
|
100% |
1068
12.7 IPS |
|
Face Detection (Q)
|
95% |
3516
42.0 IPS |
|
Depth Estimation (SP)
|
100% |
1532
11.8 IPS |
|
Depth Estimation (HP)
|
99% |
1544
11.9 IPS |
|
Depth Estimation (Q)
|
64% |
3518
32.2 IPS |
|
Style Transfer (SP)
|
89% |
3629
4.71 IPS |
|
Style Transfer (HP)
|
89% |
3655
4.74 IPS |
|
Style Transfer (Q)
|
98% |
8793
11.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
858
31.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
865
31.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
2094
77.6 IPS |
|
Text Classification (SP)
|
100% |
521
695.8 IPS |
|
Text Classification (HP)
|
100% |
519
693.0 IPS |
|
Text Classification (Q)
|
88% |
974
1.31 KIPS |
|
Machine Translation (SP)
|
100% |
769
13.3 IPS |
|
Machine Translation (HP)
|
100% |
756
13.0 IPS |
|
Machine Translation (Q)
|
50% |
475
16.9 IPS |