Upload Date | September 14 2024 01:01 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 662 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi 9T |
Model ID | Xiaomi M2010J19SG |
Motherboard | lime |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.02 GHz |
Memory Information | |
---|---|
Size | 3.63 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
28
5.18 IPS |
|
Image Classification (HP)
|
100% |
57
10.6 IPS |
|
Image Classification (Q)
|
97% |
58
10.9 IPS |
|
Image Segmentation (SP)
|
100% |
27
0.43 IPS |
|
Image Segmentation (HP)
|
100% |
91
1.48 IPS |
|
Image Segmentation (Q)
|
98% |
95
1.54 IPS |
|
Pose Estimation (SP)
|
100% |
50
0.06 IPS |
|
Pose Estimation (HP)
|
100% |
98
0.11 IPS |
|
Pose Estimation (Q)
|
95% |
99
0.12 IPS |
|
Object Detection (SP)
|
100% |
28
2.23 IPS |
|
Object Detection (HP)
|
100% |
48
3.83 IPS |
|
Object Detection (Q)
|
89% |
48
3.83 IPS |
|
Face Detection (SP)
|
100% |
71
0.84 IPS |
|
Face Detection (HP)
|
100% |
177
2.10 IPS |
|
Face Detection (Q)
|
97% |
184
2.19 IPS |
|
Depth Estimation (SP)
|
100% |
66
0.51 IPS |
|
Depth Estimation (HP)
|
99% |
136
1.05 IPS |
|
Depth Estimation (Q)
|
62% |
112
1.06 IPS |
|
Style Transfer (SP)
|
0
|
||
Style Transfer (HP)
|
100% |
259
0.33 IPS |
|
Style Transfer (Q)
|
98% |
258
0.33 IPS |
|
Image Super-Resolution (SP)
|
100% |
33
1.20 IPS |
|
Image Super-Resolution (HP)
|
100% |
70
2.58 IPS |
|
Image Super-Resolution (Q)
|
97% |
69
2.56 IPS |
|
Text Classification (SP)
|
100% |
60
80.3 IPS |
|
Text Classification (HP)
|
100% |
60
80.0 IPS |
|
Text Classification (Q)
|
91% |
76
102.7 IPS |
|
Machine Translation (SP)
|
100% |
107
1.85 IPS |
|
Machine Translation (HP)
|
100% |
108
1.86 IPS |
|
Machine Translation (Q)
|
57% |
79
1.92 IPS |