Upload Date | August 16 2024 09:55 PM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
85
15.9 IPS |
|
Image Classification (HP)
|
100% |
137
25.5 IPS |
|
Image Classification (Q)
|
97% |
142
26.5 IPS |
|
Image Segmentation (SP)
|
100% |
114
1.85 IPS |
|
Image Segmentation (HP)
|
100% |
203
3.30 IPS |
|
Image Segmentation (Q)
|
98% |
200
3.25 IPS |
|
Pose Estimation (SP)
|
100% |
166
0.19 IPS |
|
Pose Estimation (HP)
|
100% |
250
0.29 IPS |
|
Pose Estimation (Q)
|
95% |
249
0.29 IPS |
|
Object Detection (SP)
|
100% |
76
6.05 IPS |
|
Object Detection (HP)
|
100% |
117
9.26 IPS |
|
Object Detection (Q)
|
86% |
120
9.67 IPS |
|
Face Detection (SP)
|
100% |
196
2.33 IPS |
|
Face Detection (HP)
|
100% |
362
4.30 IPS |
|
Face Detection (Q)
|
97% |
387
4.61 IPS |
|
Depth Estimation (SP)
|
100% |
204
1.57 IPS |
|
Depth Estimation (HP)
|
99% |
359
2.77 IPS |
|
Depth Estimation (Q)
|
75% |
346
2.79 IPS |
|
Style Transfer (SP)
|
100% |
390
0.50 IPS |
|
Style Transfer (HP)
|
100% |
875
1.13 IPS |
|
Style Transfer (Q)
|
98% |
870
1.12 IPS |
|
Image Super-Resolution (SP)
|
100% |
100
3.71 IPS |
|
Image Super-Resolution (HP)
|
100% |
176
6.52 IPS |
|
Image Super-Resolution (Q)
|
97% |
175
6.48 IPS |
|
Text Classification (SP)
|
100% |
134
178.8 IPS |
|
Text Classification (HP)
|
100% |
134
178.7 IPS |
|
Text Classification (Q)
|
91% |
218
293.4 IPS |
|
Machine Translation (SP)
|
100% |
225
3.87 IPS |
|
Machine Translation (HP)
|
100% |
227
3.90 IPS |
|
Machine Translation (Q)
|
57% |
159
3.89 IPS |