Upload Date | December 27 2024 08:19 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 778G |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi Poco X5 Pro |
Model ID | Xiaomi 22101320G |
Motherboard | redwood |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM redwood |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.02 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
463
86.1 IPS |
|
Image Classification (HP)
|
100% |
460
85.6 IPS |
|
Image Classification (Q)
|
100% |
1442
268.2 IPS |
|
Image Segmentation (SP)
|
100% |
518
8.39 IPS |
|
Image Segmentation (HP)
|
100% |
500
8.11 IPS |
|
Image Segmentation (Q)
|
98% |
1669
27.1 IPS |
|
Pose Estimation (SP)
|
100% |
2003
2.34 IPS |
|
Pose Estimation (HP)
|
100% |
1813
2.12 IPS |
|
Pose Estimation (Q)
|
84% |
2975
3.53 IPS |
|
Object Detection (SP)
|
100% |
394
31.3 IPS |
|
Object Detection (HP)
|
100% |
394
31.2 IPS |
|
Object Detection (Q)
|
83% |
1129
91.2 IPS |
|
Face Detection (SP)
|
100% |
1033
12.3 IPS |
|
Face Detection (HP)
|
100% |
1028
12.2 IPS |
|
Face Detection (Q)
|
95% |
2796
33.4 IPS |
|
Depth Estimation (SP)
|
100% |
1425
11.0 IPS |
|
Depth Estimation (HP)
|
99% |
1450
11.2 IPS |
|
Depth Estimation (Q)
|
64% |
2736
25.1 IPS |
|
Style Transfer (SP)
|
89% |
3125
4.06 IPS |
|
Style Transfer (HP)
|
89% |
3132
4.07 IPS |
|
Style Transfer (Q)
|
98% |
6899
8.90 IPS |
|
Image Super-Resolution (SP)
|
100% |
805
29.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
807
29.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1658
61.4 IPS |
|
Text Classification (SP)
|
100% |
416
555.2 IPS |
|
Text Classification (HP)
|
100% |
412
549.8 IPS |
|
Text Classification (Q)
|
88% |
786
1.06 KIPS |
|
Machine Translation (SP)
|
100% |
650
11.2 IPS |
|
Machine Translation (HP)
|
100% |
654
11.3 IPS |
|
Machine Translation (Q)
|
50% |
386
13.7 IPS |