Upload Date | September 18 2024 07:13 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | MediaTek Dimensity 8100 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi Redmi K50i |
Model ID | Xiaomi 22041216I |
Motherboard | xagain |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.85 GHz |
Memory Information | |
---|---|
Size | 5.34 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
229
42.6 IPS |
|
Image Classification (HP)
|
100% |
225
41.9 IPS |
|
Image Classification (Q)
|
100% |
625
116.2 IPS |
|
Image Segmentation (SP)
|
100% |
262
4.25 IPS |
|
Image Segmentation (HP)
|
100% |
278
4.51 IPS |
|
Image Segmentation (Q)
|
98% |
720
11.7 IPS |
|
Pose Estimation (SP)
|
100% |
1503
1.75 IPS |
|
Pose Estimation (HP)
|
100% |
2237
2.61 IPS |
|
Pose Estimation (Q)
|
84% |
3788
4.49 IPS |
|
Object Detection (SP)
|
100% |
469
37.2 IPS |
|
Object Detection (HP)
|
100% |
504
39.9 IPS |
|
Object Detection (Q)
|
83% |
1407
113.6 IPS |
|
Face Detection (SP)
|
100% |
1333
15.8 IPS |
|
Face Detection (HP)
|
100% |
1561
18.6 IPS |
|
Face Detection (Q)
|
95% |
3471
41.4 IPS |
|
Depth Estimation (SP)
|
100% |
2018
15.5 IPS |
|
Depth Estimation (HP)
|
99% |
2006
15.5 IPS |
|
Depth Estimation (Q)
|
64% |
3442
31.5 IPS |
|
Style Transfer (SP)
|
89% |
3978
5.16 IPS |
|
Style Transfer (HP)
|
89% |
3821
4.96 IPS |
|
Style Transfer (Q)
|
98% |
8520
11.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
1213
44.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
976
36.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
1563
57.9 IPS |
|
Text Classification (SP)
|
100% |
589
786.7 IPS |
|
Text Classification (HP)
|
100% |
624
832.9 IPS |
|
Text Classification (Q)
|
88% |
1156
1.56 KIPS |
|
Machine Translation (SP)
|
100% |
848
14.6 IPS |
|
Machine Translation (HP)
|
100% |
874
15.0 IPS |
|
Machine Translation (Q)
|
50% |
538
19.1 IPS |