Upload Date | November 21 2024 05:54 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 2201116PG |
Model ID | Xiaomi 2201116PG |
Motherboard | veux |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
242
44.9 IPS |
|
Image Classification (HP)
|
100% |
241
44.7 IPS |
|
Image Classification (Q)
|
100% |
728
135.4 IPS |
|
Image Segmentation (SP)
|
100% |
310
5.02 IPS |
|
Image Segmentation (HP)
|
100% |
313
5.08 IPS |
|
Image Segmentation (Q)
|
98% |
832
13.5 IPS |
|
Pose Estimation (SP)
|
100% |
1187
1.39 IPS |
|
Pose Estimation (HP)
|
100% |
1193
1.39 IPS |
|
Pose Estimation (Q)
|
84% |
1740
2.06 IPS |
|
Object Detection (SP)
|
100% |
240
19.0 IPS |
|
Object Detection (HP)
|
100% |
241
19.1 IPS |
|
Object Detection (Q)
|
83% |
720
58.1 IPS |
|
Face Detection (SP)
|
100% |
770
9.16 IPS |
|
Face Detection (HP)
|
100% |
770
9.15 IPS |
|
Face Detection (Q)
|
95% |
1723
20.6 IPS |
|
Depth Estimation (SP)
|
100% |
1021
7.87 IPS |
|
Depth Estimation (HP)
|
99% |
1018
7.84 IPS |
|
Depth Estimation (Q)
|
64% |
1630
14.9 IPS |
|
Style Transfer (SP)
|
89% |
2026
2.63 IPS |
|
Style Transfer (HP)
|
89% |
2020
2.62 IPS |
|
Style Transfer (Q)
|
98% |
4037
5.21 IPS |
|
Image Super-Resolution (SP)
|
100% |
544
20.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
530
19.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1011
37.5 IPS |
|
Text Classification (SP)
|
100% |
295
393.9 IPS |
|
Text Classification (HP)
|
100% |
291
388.6 IPS |
|
Text Classification (Q)
|
88% |
594
801.1 IPS |
|
Machine Translation (SP)
|
100% |
495
8.52 IPS |
|
Machine Translation (HP)
|
100% |
494
8.51 IPS |
|
Machine Translation (Q)
|
50% |
386
13.7 IPS |