Upload Date | November 17 2024 10:14 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm Snapdragon 865 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Poco F2 Pro |
Model ID | Xiaomi POCO F2 Pro |
Motherboard | lmi |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 5.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
441
82.1 IPS |
|
Image Classification (HP)
|
100% |
727
135.3 IPS |
|
Image Classification (Q)
|
97% |
1390
259.4 IPS |
|
Image Segmentation (SP)
|
100% |
632
10.2 IPS |
|
Image Segmentation (HP)
|
100% |
164
2.65 IPS |
|
Image Segmentation (Q)
|
98% |
1328
21.6 IPS |
|
Pose Estimation (SP)
|
100% |
1436
1.68 IPS |
|
Pose Estimation (HP)
|
100% |
5489
6.40 IPS |
|
Pose Estimation (Q)
|
96% |
11578
13.6 IPS |
|
Object Detection (SP)
|
100% |
420
33.3 IPS |
|
Object Detection (HP)
|
100% |
102
8.06 IPS |
|
Object Detection (Q)
|
85% |
1658
133.5 IPS |
|
Face Detection (SP)
|
100% |
1185
14.1 IPS |
|
Face Detection (HP)
|
100% |
266
3.16 IPS |
|
Face Detection (Q)
|
97% |
3805
45.4 IPS |
|
Depth Estimation (SP)
|
99% |
423
3.26 IPS |
|
Depth Estimation (HP)
|
99% |
263
2.02 IPS |
|
Depth Estimation (Q)
|
22% |
260
59.5 IPS |
|
Style Transfer (SP)
|
100% |
648
0.83 IPS |
|
Style Transfer (HP)
|
100% |
447
0.57 IPS |
|
Style Transfer (Q)
|
98% |
3480
4.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
746
27.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
2133
78.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
5403
200.2 IPS |
|
Text Classification (SP)
|
71% |
9
12.5 IPS |
|
Text Classification (HP)
|
100% |
146
194.9 IPS |
|
Text Classification (Q)
|
93% |
145
195.3 IPS |
|
Machine Translation (SP)
|
100% |
241
4.16 IPS |
|
Machine Translation (HP)
|
100% |
300
5.17 IPS |
|
Machine Translation (Q)
|
54% |
204
5.76 IPS |