Upload Date | February 12 2024 07:45 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 21121210G |
Model ID | Xiaomi 21121210G |
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 |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
122
22.8 IPS |
|
Image Classification (F16)
|
100% |
122
22.7 IPS |
|
Image Classification (I8)
|
97% |
323
60.4 IPS |
|
Image Segmentation (F32)
|
100% |
156
2.61 IPS |
|
Image Segmentation (F16)
|
100% |
156
2.60 IPS |
|
Image Segmentation (I8)
|
98% |
339
5.67 IPS |
|
Pose Estimation (F32)
|
100% |
213
0.26 IPS |
|
Pose Estimation (F16)
|
100% |
214
0.26 IPS |
|
Pose Estimation (I8)
|
100% |
825
1.00 IPS |
|
Object Detection (F32)
|
100% |
128
9.56 IPS |
|
Object Detection (F16)
|
100% |
128
9.54 IPS |
|
Object Detection (I8)
|
61% |
367
27.4 IPS |
|
Face Detection (F32)
|
100% |
327
3.89 IPS |
|
Face Detection (F16)
|
100% |
328
3.90 IPS |
|
Face Detection (I8)
|
86% |
717
8.52 IPS |
|
Depth Estimation (F32)
|
100% |
279
2.17 IPS |
|
Depth Estimation (F16)
|
100% |
279
2.17 IPS |
|
Depth Estimation (I8)
|
95% |
793
6.15 IPS |
|
Style Transfer (F32)
|
100% |
491
0.65 IPS |
|
Style Transfer (F16)
|
100% |
460
0.60 IPS |
|
Style Transfer (I8)
|
98% |
1179
1.55 IPS |
|
Image Super-Resolution (F32)
|
100% |
132
4.70 IPS |
|
Image Super-Resolution (F16)
|
100% |
132
4.73 IPS |
|
Image Super-Resolution (I8)
|
98% |
515
18.4 IPS |
|
Text Classification (F32)
|
100% |
163
233.9 IPS |
|
Text Classification (F16)
|
100% |
161
231.4 IPS |
|
Text Classification (I8)
|
92% |
301
431.9 IPS |
|
Machine Translation (F32)
|
100% |
343
6.31 IPS |
|
Machine Translation (F16)
|
100% |
303
5.58 IPS |
|
Machine Translation (I8)
|
64% |
350
6.44 IPS |