Upload Date | May 26 2024 05:20 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi Mi A3 |
Model ID | Xiaomi Mi A3 |
Motherboard | trinket |
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 | 3.56 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
142
26.6 IPS |
|
Image Classification (F16)
|
100% |
139
26.1 IPS |
|
Image Classification (I8)
|
97% |
213
39.8 IPS |
|
Image Segmentation (F32)
|
100% |
188
3.14 IPS |
|
Image Segmentation (F16)
|
100% |
189
3.16 IPS |
|
Image Segmentation (I8)
|
98% |
214
3.58 IPS |
|
Pose Estimation (F32)
|
100% |
233
0.28 IPS |
|
Pose Estimation (F16)
|
100% |
232
0.28 IPS |
|
Pose Estimation (I8)
|
100% |
651
0.79 IPS |
|
Object Detection (F32)
|
100% |
141
10.5 IPS |
|
Object Detection (F16)
|
100% |
136
10.1 IPS |
|
Object Detection (I8)
|
61% |
225
16.8 IPS |
|
Face Detection (F32)
|
100% |
290
3.44 IPS |
|
Face Detection (F16)
|
100% |
285
3.39 IPS |
|
Face Detection (I8)
|
86% |
505
6.00 IPS |
|
Depth Estimation (F32)
|
100% |
275
2.13 IPS |
|
Depth Estimation (F16)
|
100% |
218
1.69 IPS |
|
Depth Estimation (I8)
|
95% |
428
3.32 IPS |
|
Style Transfer (F32)
|
100% |
404
0.53 IPS |
|
Style Transfer (F16)
|
100% |
377
0.50 IPS |
|
Style Transfer (I8)
|
98% |
1044
1.37 IPS |
|
Image Super-Resolution (F32)
|
100% |
159
5.67 IPS |
|
Image Super-Resolution (F16)
|
100% |
143
5.11 IPS |
|
Image Super-Resolution (I8)
|
98% |
288
10.3 IPS |
|
Text Classification (F32)
|
100% |
158
227.1 IPS |
|
Text Classification (F16)
|
100% |
171
246.4 IPS |
|
Text Classification (I8)
|
92% |
140
201.2 IPS |
|
Machine Translation (F32)
|
100% |
322
5.93 IPS |
|
Machine Translation (F16)
|
100% |
232
4.27 IPS |
|
Machine Translation (I8)
|
64% |
134
2.46 IPS |