Upload Date | August 16 2024 10:20 PM |
Views | 9 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm Snapdragon 730 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi Mi 9T |
Model ID | Xiaomi Mi 9T |
Motherboard | sm6150 |
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 @ 2.21 GHz |
Memory Information | |
---|---|
Size | 5.38 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
93
17.4 IPS |
|
Image Classification (HP)
|
100% |
93
17.3 IPS |
|
Image Classification (Q)
|
97% |
212
39.6 IPS |
|
Image Segmentation (SP)
|
100% |
128
2.07 IPS |
|
Image Segmentation (HP)
|
100% |
128
2.08 IPS |
|
Image Segmentation (Q)
|
98% |
230
3.73 IPS |
|
Pose Estimation (SP)
|
100% |
172
0.20 IPS |
|
Pose Estimation (HP)
|
100% |
172
0.20 IPS |
|
Pose Estimation (Q)
|
98% |
638
0.75 IPS |
|
Object Detection (SP)
|
100% |
94
7.44 IPS |
|
Object Detection (HP)
|
100% |
94
7.49 IPS |
|
Object Detection (Q)
|
89% |
232
18.6 IPS |
|
Face Detection (SP)
|
100% |
234
2.78 IPS |
|
Face Detection (HP)
|
100% |
236
2.81 IPS |
|
Face Detection (Q)
|
97% |
466
5.56 IPS |
|
Depth Estimation (SP)
|
100% |
198
1.52 IPS |
|
Depth Estimation (HP)
|
100% |
199
1.53 IPS |
|
Depth Estimation (Q)
|
73% |
489
4.00 IPS |
|
Style Transfer (SP)
|
100% |
338
0.43 IPS |
|
Style Transfer (HP)
|
100% |
338
0.43 IPS |
|
Style Transfer (Q)
|
98% |
992
1.28 IPS |
|
Image Super-Resolution (SP)
|
100% |
99
3.64 IPS |
|
Image Super-Resolution (HP)
|
100% |
99
3.64 IPS |
|
Image Super-Resolution (Q)
|
97% |
337
12.5 IPS |
|
Text Classification (SP)
|
100% |
133
178.2 IPS |
|
Text Classification (HP)
|
100% |
133
177.3 IPS |
|
Text Classification (Q)
|
91% |
218
293.0 IPS |
|
Machine Translation (SP)
|
100% |
222
3.82 IPS |
|
Machine Translation (HP)
|
100% |
227
3.90 IPS |
|
Machine Translation (Q)
|
57% |
157
3.83 IPS |