Upload Date | June 17 2025 06:28 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Qualcomm |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 2209116AG |
Model ID | Xiaomi 2209116AG |
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% |
86
16.0 IPS |
|
Image Classification (HP)
|
100% |
140
26.0 IPS |
|
Image Classification (Q)
|
97% |
148
27.6 IPS |
|
Image Segmentation (SP)
|
100% |
98
1.59 IPS |
|
Image Segmentation (HP)
|
100% |
197
3.19 IPS |
|
Image Segmentation (Q)
|
98% |
225
3.65 IPS |
|
Pose Estimation (SP)
|
100% |
212
0.25 IPS |
|
Pose Estimation (HP)
|
100% |
251
0.29 IPS |
|
Pose Estimation (Q)
|
95% |
251
0.29 IPS |
|
Object Detection (SP)
|
100% |
75
5.94 IPS |
|
Object Detection (HP)
|
100% |
101
7.99 IPS |
|
Object Detection (Q)
|
89% |
115
9.19 IPS |
|
Face Detection (SP)
|
100% |
195
2.31 IPS |
|
Face Detection (HP)
|
100% |
368
4.37 IPS |
|
Face Detection (Q)
|
97% |
366
4.36 IPS |
|
Depth Estimation (SP)
|
100% |
211
1.63 IPS |
|
Depth Estimation (HP)
|
99% |
354
2.74 IPS |
|
Depth Estimation (Q)
|
62% |
288
2.73 IPS |
|
Style Transfer (SP)
|
100% |
397
0.51 IPS |
|
Style Transfer (HP)
|
100% |
849
1.09 IPS |
|
Style Transfer (Q)
|
98% |
845
1.09 IPS |
|
Image Super-Resolution (SP)
|
100% |
103
3.82 IPS |
|
Image Super-Resolution (HP)
|
100% |
167
6.17 IPS |
|
Image Super-Resolution (Q)
|
97% |
159
5.89 IPS |
|
Text Classification (SP)
|
100% |
111
148.2 IPS |
|
Text Classification (HP)
|
100% |
111
148.5 IPS |
|
Text Classification (Q)
|
91% |
180
242.4 IPS |
|
Machine Translation (SP)
|
100% |
196
3.38 IPS |
|
Machine Translation (HP)
|
100% |
198
3.40 IPS |
|
Machine Translation (Q)
|
57% |
143
3.50 IPS |