Upload Date | August 29 2024 11:12 AM |
Views | 17 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm Snapdragon 732G |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi Redmi Note 10 Pro |
Model ID | Xiaomi M2101K6G |
Motherboard | sweet |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.30 GHz |
Memory Information | |
---|---|
Size | 7.39 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
184
34.3 IPS |
|
Image Classification (HP)
|
100% |
245
45.5 IPS |
|
Image Classification (Q)
|
97% |
546
101.8 IPS |
|
Image Segmentation (SP)
|
100% |
209
3.38 IPS |
|
Image Segmentation (HP)
|
100% |
134
2.17 IPS |
|
Image Segmentation (Q)
|
98% |
696
11.3 IPS |
|
Pose Estimation (SP)
|
100% |
528
0.62 IPS |
|
Pose Estimation (HP)
|
100% |
1212
1.41 IPS |
|
Pose Estimation (Q)
|
96% |
4119
4.82 IPS |
|
Object Detection (SP)
|
100% |
170
13.5 IPS |
|
Object Detection (HP)
|
100% |
80
6.33 IPS |
|
Object Detection (Q)
|
89% |
559
44.7 IPS |
|
Face Detection (SP)
|
100% |
383
4.55 IPS |
|
Face Detection (HP)
|
100% |
207
2.46 IPS |
|
Face Detection (Q)
|
97% |
1397
16.7 IPS |
|
Depth Estimation (SP)
|
99% |
259
2.00 IPS |
|
Depth Estimation (HP)
|
100% |
177
1.36 IPS |
|
Depth Estimation (Q)
|
46% |
1118
22.5 IPS |
|
Style Transfer (SP)
|
100% |
426
0.55 IPS |
|
Style Transfer (HP)
|
100% |
299
0.38 IPS |
|
Style Transfer (Q)
|
98% |
1690
2.18 IPS |
|
Image Super-Resolution (SP)
|
100% |
310
11.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
576
21.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
1737
64.4 IPS |
|
Text Classification (SP)
|
71% |
2
3.34 IPS |
|
Text Classification (HP)
|
100% |
142
189.0 IPS |
|
Text Classification (Q)
|
93% |
42
56.8 IPS |
|
Machine Translation (SP)
|
100% |
93
1.59 IPS |
|
Machine Translation (HP)
|
100% |
260
4.47 IPS |
|
Machine Translation (Q)
|
54% |
113
3.20 IPS |