Upload Date | December 31 2024 12:47 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | MediaTek Dimensity 1100 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi Poco X3 GT |
Model ID | Xiaomi 21061110AG |
Motherboard | chopin |
CPU Information | |
---|---|
Name | ARM MT6891Z/CZA |
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 @ 2.60 GHz |
Memory Information | |
---|---|
Size | 7.30 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
242
45.0 IPS |
|
Image Classification (HP)
|
100% |
158
29.4 IPS |
|
Image Classification (Q)
|
100% |
513
95.4 IPS |
|
Image Segmentation (SP)
|
100% |
233
3.77 IPS |
|
Image Segmentation (HP)
|
100% |
243
3.93 IPS |
|
Image Segmentation (Q)
|
98% |
469
7.63 IPS |
|
Pose Estimation (SP)
|
100% |
813
0.95 IPS |
|
Pose Estimation (HP)
|
100% |
763
0.89 IPS |
|
Pose Estimation (Q)
|
84% |
1257
1.49 IPS |
|
Object Detection (SP)
|
100% |
188
14.9 IPS |
|
Object Detection (HP)
|
100% |
197
15.7 IPS |
|
Object Detection (Q)
|
83% |
480
38.8 IPS |
|
Face Detection (SP)
|
100% |
608
7.22 IPS |
|
Face Detection (HP)
|
100% |
574
6.82 IPS |
|
Face Detection (Q)
|
95% |
1212
14.5 IPS |
|
Depth Estimation (SP)
|
100% |
742
5.71 IPS |
|
Depth Estimation (HP)
|
99% |
689
5.31 IPS |
|
Depth Estimation (Q)
|
64% |
883
8.09 IPS |
|
Style Transfer (SP)
|
89% |
1550
2.01 IPS |
|
Style Transfer (HP)
|
89% |
1476
1.92 IPS |
|
Style Transfer (Q)
|
98% |
3096
3.99 IPS |
|
Image Super-Resolution (SP)
|
100% |
377
13.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
439
16.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
667
24.7 IPS |
|
Text Classification (SP)
|
100% |
202
269.9 IPS |
|
Text Classification (HP)
|
100% |
189
252.4 IPS |
|
Text Classification (Q)
|
88% |
349
471.0 IPS |
|
Machine Translation (SP)
|
100% |
315
5.43 IPS |
|
Machine Translation (HP)
|
100% |
263
4.53 IPS |
|
Machine Translation (Q)
|
50% |
183
6.51 IPS |