Upload Date | August 23 2024 06:55 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2201122C |
Model ID | Xiaomi 2201122C |
Motherboard | taro |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.50 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 7.04 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
185
34.4 IPS |
|
Image Classification (HP)
|
100% |
198
36.8 IPS |
|
Image Classification (Q)
|
97% |
523
97.6 IPS |
|
Image Segmentation (SP)
|
100% |
200
3.25 IPS |
|
Image Segmentation (HP)
|
100% |
157
2.55 IPS |
|
Image Segmentation (Q)
|
98% |
340
5.52 IPS |
|
Pose Estimation (SP)
|
100% |
241
0.28 IPS |
|
Pose Estimation (HP)
|
100% |
211
0.25 IPS |
|
Pose Estimation (Q)
|
98% |
821
0.96 IPS |
|
Object Detection (SP)
|
100% |
115
9.14 IPS |
|
Object Detection (HP)
|
100% |
115
9.13 IPS |
|
Object Detection (Q)
|
89% |
346
27.7 IPS |
|
Face Detection (SP)
|
100% |
324
3.85 IPS |
|
Face Detection (HP)
|
100% |
326
3.88 IPS |
|
Face Detection (Q)
|
97% |
760
9.06 IPS |
|
Depth Estimation (SP)
|
100% |
270
2.08 IPS |
|
Depth Estimation (HP)
|
100% |
273
2.10 IPS |
|
Depth Estimation (Q)
|
73% |
734
6.00 IPS |
|
Style Transfer (SP)
|
100% |
481
0.62 IPS |
|
Style Transfer (HP)
|
100% |
481
0.62 IPS |
|
Style Transfer (Q)
|
98% |
1228
1.58 IPS |
|
Image Super-Resolution (SP)
|
100% |
127
4.69 IPS |
|
Image Super-Resolution (HP)
|
100% |
126
4.66 IPS |
|
Image Super-Resolution (Q)
|
97% |
476
17.6 IPS |
|
Text Classification (SP)
|
100% |
164
219.4 IPS |
|
Text Classification (HP)
|
100% |
166
221.5 IPS |
|
Text Classification (Q)
|
91% |
303
407.5 IPS |
|
Machine Translation (SP)
|
100% |
293
5.04 IPS |
|
Machine Translation (HP)
|
100% |
294
5.06 IPS |
|
Machine Translation (Q)
|
57% |
257
6.27 IPS |