Upload Date | December 26 2024 10:20 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | MediaTek Dimensity 8300 Ultra |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi Poco X6 Pro |
Model ID | Xiaomi 2311DRK48G |
Motherboard | duchamp |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3405 revision 0 |
Base Frequency | 2.20 GHz |
Cluster 1 | 4 Cores @ 2.20 GHz |
Cluster 2 | 3 Cores @ 3.20 GHz |
Cluster 3 | 1 Core @ 3.35 GHz |
Memory Information | |
---|---|
Size | 7.17 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
563
104.8 IPS |
|
Image Classification (HP)
|
100% |
3822
710.7 IPS |
|
Image Classification (Q)
|
99% |
7304
1.36 KIPS |
|
Image Segmentation (SP)
|
100% |
522
8.46 IPS |
|
Image Segmentation (HP)
|
100% |
4128
66.9 IPS |
|
Image Segmentation (Q)
|
98% |
1780
28.9 IPS |
|
Pose Estimation (SP)
|
100% |
4880
5.69 IPS |
|
Pose Estimation (HP)
|
100% |
17702
20.7 IPS |
|
Pose Estimation (Q)
|
95% |
71844
84.2 IPS |
|
Object Detection (SP)
|
100% |
460
36.5 IPS |
|
Object Detection (HP)
|
100% |
4212
334.1 IPS |
|
Object Detection (Q)
|
86% |
4653
374.3 IPS |
|
Face Detection (SP)
|
100% |
2030
24.1 IPS |
|
Face Detection (HP)
|
100% |
9957
118.3 IPS |
|
Face Detection (Q)
|
97% |
10843
129.3 IPS |
|
Depth Estimation (SP)
|
100% |
627
4.83 IPS |
|
Depth Estimation (HP)
|
99% |
18487
142.4 IPS |
|
Depth Estimation (Q)
|
62% |
29782
282.8 IPS |
|
Style Transfer (SP)
|
100% |
2122
2.73 IPS |
|
Style Transfer (HP)
|
100% |
500
0.64 IPS |
|
Style Transfer (Q)
|
30% |
409
6.16 IPS |
|
Image Super-Resolution (SP)
|
100% |
1532
56.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
9979
368.5 IPS |
|
Image Super-Resolution (Q)
|
41% |
6900
1.00 KIPS |
|
Text Classification (SP)
|
100% |
67
89.7 IPS |
|
Text Classification (HP)
|
100% |
1554
2.07 KIPS |
|
Text Classification (Q)
|
93% |
1568
2.10 KIPS |
|
Machine Translation (SP)
|
100% |
257
4.42 IPS |
|
Machine Translation (HP)
|
100% |
1309
22.5 IPS |
|
Machine Translation (Q)
|
60% |
316
7.12 IPS |