Upload Date | December 27 2024 09:28 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2201123C |
Model ID | Xiaomi 2201123C |
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% |
123
22.8 IPS |
|
Image Classification (HP)
|
100% |
123
22.9 IPS |
|
Image Classification (Q)
|
99% |
325
60.7 IPS |
|
Image Segmentation (SP)
|
100% |
161
2.61 IPS |
|
Image Segmentation (HP)
|
100% |
162
2.62 IPS |
|
Image Segmentation (Q)
|
98% |
350
5.69 IPS |
|
Pose Estimation (SP)
|
100% |
220
0.26 IPS |
|
Pose Estimation (HP)
|
100% |
221
0.26 IPS |
|
Pose Estimation (Q)
|
98% |
853
1.00 IPS |
|
Object Detection (SP)
|
100% |
122
9.71 IPS |
|
Object Detection (HP)
|
100% |
123
9.75 IPS |
|
Object Detection (Q)
|
87% |
354
28.4 IPS |
|
Face Detection (SP)
|
100% |
328
3.90 IPS |
|
Face Detection (HP)
|
100% |
331
3.93 IPS |
|
Face Detection (Q)
|
97% |
714
8.51 IPS |
|
Depth Estimation (SP)
|
100% |
282
2.17 IPS |
|
Depth Estimation (HP)
|
99% |
283
2.18 IPS |
|
Depth Estimation (Q)
|
64% |
680
6.17 IPS |
|
Style Transfer (SP)
|
100% |
559
0.72 IPS |
|
Style Transfer (HP)
|
100% |
499
0.64 IPS |
|
Style Transfer (Q)
|
98% |
1357
1.75 IPS |
|
Image Super-Resolution (SP)
|
100% |
139
5.14 IPS |
|
Image Super-Resolution (HP)
|
100% |
140
5.16 IPS |
|
Image Super-Resolution (Q)
|
97% |
489
18.1 IPS |
|
Text Classification (SP)
|
100% |
180
240.2 IPS |
|
Text Classification (HP)
|
100% |
180
240.8 IPS |
|
Text Classification (Q)
|
91% |
318
426.9 IPS |
|
Machine Translation (SP)
|
100% |
310
5.33 IPS |
|
Machine Translation (HP)
|
100% |
309
5.33 IPS |
|
Machine Translation (Q)
|
57% |
276
6.73 IPS |