Upload Date | December 24 2024 10:21 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 720G |
System Information | |
---|---|
Operating System | Android 12 |
Model | Realme 7 Pro |
Model ID | realme RMX2170 |
Motherboard | atoll |
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 | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
236
43.9 IPS |
|
Image Classification (HP)
|
100% |
226
42.1 IPS |
|
Image Classification (Q)
|
100% |
698
129.7 IPS |
|
Image Segmentation (SP)
|
100% |
291
4.71 IPS |
|
Image Segmentation (HP)
|
100% |
296
4.80 IPS |
|
Image Segmentation (Q)
|
98% |
749
12.2 IPS |
|
Pose Estimation (SP)
|
100% |
1149
1.34 IPS |
|
Pose Estimation (HP)
|
100% |
1125
1.31 IPS |
|
Pose Estimation (Q)
|
84% |
1711
2.03 IPS |
|
Object Detection (SP)
|
100% |
237
18.8 IPS |
|
Object Detection (HP)
|
100% |
237
18.8 IPS |
|
Object Detection (Q)
|
83% |
693
56.0 IPS |
|
Face Detection (SP)
|
100% |
704
8.37 IPS |
|
Face Detection (HP)
|
100% |
703
8.35 IPS |
|
Face Detection (Q)
|
95% |
1566
18.7 IPS |
|
Depth Estimation (SP)
|
100% |
955
7.36 IPS |
|
Depth Estimation (HP)
|
99% |
959
7.39 IPS |
|
Depth Estimation (Q)
|
64% |
1576
14.4 IPS |
|
Style Transfer (SP)
|
89% |
1890
2.45 IPS |
|
Style Transfer (HP)
|
89% |
1898
2.46 IPS |
|
Style Transfer (Q)
|
98% |
3931
5.07 IPS |
|
Image Super-Resolution (SP)
|
100% |
481
17.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
492
18.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
966
35.8 IPS |
|
Text Classification (SP)
|
100% |
280
373.6 IPS |
|
Text Classification (HP)
|
100% |
281
375.7 IPS |
|
Text Classification (Q)
|
88% |
527
711.2 IPS |
|
Machine Translation (SP)
|
100% |
480
8.28 IPS |
|
Machine Translation (HP)
|
100% |
474
8.16 IPS |
|
Machine Translation (Q)
|
50% |
344
12.2 IPS |