Upload Date | November 23 2024 08:57 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 720G |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi Note 9 Pro |
Model ID | Xiaomi Redmi Note 9 Pro |
Motherboard | joyeuse |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 15 part 2052 revision 15 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.32 GHz |
Memory Information | |
---|---|
Size | 5.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
235
43.6 IPS |
|
Image Classification (HP)
|
100% |
233
43.4 IPS |
|
Image Classification (Q)
|
100% |
698
129.8 IPS |
|
Image Segmentation (SP)
|
100% |
291
4.72 IPS |
|
Image Segmentation (HP)
|
100% |
291
4.72 IPS |
|
Image Segmentation (Q)
|
98% |
743
12.1 IPS |
|
Pose Estimation (SP)
|
100% |
1113
1.30 IPS |
|
Pose Estimation (HP)
|
100% |
1122
1.31 IPS |
|
Pose Estimation (Q)
|
84% |
1714
2.03 IPS |
|
Object Detection (SP)
|
100% |
238
18.9 IPS |
|
Object Detection (HP)
|
100% |
239
18.9 IPS |
|
Object Detection (Q)
|
83% |
697
56.3 IPS |
|
Face Detection (SP)
|
100% |
700
8.32 IPS |
|
Face Detection (HP)
|
100% |
707
8.40 IPS |
|
Face Detection (Q)
|
95% |
1567
18.7 IPS |
|
Depth Estimation (SP)
|
100% |
849
6.54 IPS |
|
Depth Estimation (HP)
|
99% |
848
6.54 IPS |
|
Depth Estimation (Q)
|
64% |
1501
13.7 IPS |
|
Style Transfer (SP)
|
89% |
1878
2.44 IPS |
|
Style Transfer (HP)
|
89% |
1913
2.48 IPS |
|
Style Transfer (Q)
|
98% |
3882
5.01 IPS |
|
Image Super-Resolution (SP)
|
100% |
496
18.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
502
18.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
964
35.7 IPS |
|
Text Classification (SP)
|
100% |
285
380.0 IPS |
|
Text Classification (HP)
|
100% |
286
381.6 IPS |
|
Text Classification (Q)
|
88% |
532
716.9 IPS |
|
Machine Translation (SP)
|
100% |
487
8.39 IPS |
|
Machine Translation (HP)
|
100% |
485
8.36 IPS |
|
Machine Translation (Q)
|
50% |
349
12.4 IPS |