Upload Date | September 18 2024 09:13 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8+ Gen 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 12T Pro |
Model ID | Xiaomi 22081212UG |
Motherboard | diting |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 4 Cores @ 2.02 GHz |
Cluster 2 | 3 Cores @ 2.75 GHz |
Cluster 3 | 1 Core @ 3.19 GHz |
Memory Information | |
---|---|
Size | 7.04 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
658
122.4 IPS |
|
Image Classification (HP)
|
100% |
606
112.6 IPS |
|
Image Classification (Q)
|
100% |
2460
457.4 IPS |
|
Image Segmentation (SP)
|
100% |
692
11.2 IPS |
|
Image Segmentation (HP)
|
100% |
736
11.9 IPS |
|
Image Segmentation (Q)
|
98% |
2588
42.1 IPS |
|
Pose Estimation (SP)
|
100% |
2591
3.02 IPS |
|
Pose Estimation (HP)
|
100% |
2595
3.03 IPS |
|
Pose Estimation (Q)
|
84% |
5819
6.90 IPS |
|
Object Detection (SP)
|
100% |
560
44.4 IPS |
|
Object Detection (HP)
|
100% |
557
44.2 IPS |
|
Object Detection (Q)
|
83% |
2049
165.5 IPS |
|
Face Detection (SP)
|
100% |
1894
22.5 IPS |
|
Face Detection (HP)
|
100% |
1876
22.3 IPS |
|
Face Detection (Q)
|
95% |
4241
50.6 IPS |
|
Depth Estimation (SP)
|
100% |
2464
19.0 IPS |
|
Depth Estimation (HP)
|
99% |
2376
18.3 IPS |
|
Depth Estimation (Q)
|
64% |
4355
39.9 IPS |
|
Style Transfer (SP)
|
89% |
3971
5.15 IPS |
|
Style Transfer (HP)
|
89% |
3791
4.92 IPS |
|
Style Transfer (Q)
|
98% |
9811
12.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
1163
43.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1092
40.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
2245
83.2 IPS |
|
Text Classification (SP)
|
100% |
409
545.5 IPS |
|
Text Classification (HP)
|
100% |
404
539.0 IPS |
|
Text Classification (Q)
|
88% |
762
1.03 KIPS |
|
Machine Translation (SP)
|
100% |
649
11.2 IPS |
|
Machine Translation (HP)
|
100% |
712
12.3 IPS |
|
Machine Translation (Q)
|
50% |
521
18.5 IPS |