User | Slich2 |
Upload Date | January 04 2025 06:04 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | MediaTek Dimensity 9200+ |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 13T Pro |
Model ID | Xiaomi 23078PND5G |
Motherboard | corot |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 3 Cores @ 3.00 GHz |
Cluster 3 | 1 Core @ 3.35 GHz |
Memory Information | |
---|---|
Size | 15.01 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
665
123.7 IPS |
|
Image Classification (HP)
|
100% |
2583
480.3 IPS |
|
Image Classification (Q)
|
99% |
6302
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
388
6.29 IPS |
|
Image Segmentation (HP)
|
100% |
2536
41.1 IPS |
|
Image Segmentation (Q)
|
98% |
1255
20.4 IPS |
|
Pose Estimation (SP)
|
100% |
2791
3.26 IPS |
|
Pose Estimation (HP)
|
100% |
8117
9.47 IPS |
|
Pose Estimation (Q)
|
95% |
32963
38.6 IPS |
|
Object Detection (SP)
|
100% |
475
37.7 IPS |
|
Object Detection (HP)
|
100% |
2316
183.7 IPS |
|
Object Detection (Q)
|
86% |
3565
286.8 IPS |
|
Face Detection (SP)
|
28% |
97
18.0 IPS |
|
Face Detection (HP)
|
100% |
6877
81.7 IPS |
|
Face Detection (Q)
|
97% |
10182
121.4 IPS |
|
Depth Estimation (SP)
|
100% |
851
6.56 IPS |
|
Depth Estimation (HP)
|
99% |
9891
76.2 IPS |
|
Depth Estimation (Q)
|
62% |
23113
219.5 IPS |
|
Style Transfer (SP)
|
100% |
1953
2.51 IPS |
|
Style Transfer (HP)
|
100% |
665
0.86 IPS |
|
Style Transfer (Q)
|
30% |
414
6.25 IPS |
|
Image Super-Resolution (SP)
|
100% |
1122
41.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
5344
197.3 IPS |
|
Image Super-Resolution (Q)
|
41% |
4214
613.8 IPS |
|
Text Classification (SP)
|
100% |
65
86.1 IPS |
|
Text Classification (HP)
|
100% |
319
425.3 IPS |
|
Text Classification (Q)
|
93% |
952
1.28 KIPS |
|
Machine Translation (SP)
|
100% |
272
4.68 IPS |
|
Machine Translation (HP)
|
100% |
453
7.81 IPS |
|
Machine Translation (Q)
|
60% |
339
7.63 IPS |