Upload Date | October 01 2024 12:46 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI MAO-LX9 |
Model ID | HUAWEI MAO-LX9 |
Motherboard | MAO |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3337 revision 0 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores @ 1.90 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.47 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
147
27.5 IPS |
|
Image Classification (F16)
|
100% |
144
27.0 IPS |
|
Image Classification (I8)
|
97% |
203
38.0 IPS |
|
Image Segmentation (F32)
|
100% |
195
3.26 IPS |
|
Image Segmentation (F16)
|
100% |
190
3.18 IPS |
|
Image Segmentation (I8)
|
98% |
79
1.31 IPS |
|
Pose Estimation (F32)
|
100% |
114
0.14 IPS |
|
Pose Estimation (F16)
|
100% |
114
0.14 IPS |
|
Pose Estimation (I8)
|
100% |
222
0.27 IPS |
|
Object Detection (F32)
|
100% |
35
2.58 IPS |
|
Object Detection (F16)
|
100% |
35
2.63 IPS |
|
Object Detection (I8)
|
61% |
48
3.56 IPS |
|
Face Detection (F32)
|
100% |
101
1.20 IPS |
|
Face Detection (F16)
|
100% |
102
1.21 IPS |
|
Face Detection (I8)
|
86% |
155
1.84 IPS |
|
Depth Estimation (F32)
|
100% |
95
0.74 IPS |
|
Depth Estimation (F16)
|
100% |
94
0.73 IPS |
|
Depth Estimation (I8)
|
95% |
142
1.10 IPS |
|
Style Transfer (F32)
|
100% |
211
0.28 IPS |
|
Style Transfer (F16)
|
100% |
212
0.28 IPS |
|
Style Transfer (I8)
|
98% |
440
0.58 IPS |
|
Image Super-Resolution (F32)
|
100% |
54
1.94 IPS |
|
Image Super-Resolution (F16)
|
100% |
53
1.91 IPS |
|
Image Super-Resolution (I8)
|
98% |
87
3.09 IPS |
|
Text Classification (F32)
|
100% |
7
10.3 IPS |
|
Text Classification (F16)
|
100% |
7
9.46 IPS |
|
Text Classification (I8)
|
92% |
8
10.9 IPS |
|
Machine Translation (F32)
|
100% |
16
0.30 IPS |
|
Machine Translation (F16)
|
100% |
16
0.30 IPS |
|
Machine Translation (I8)
|
64% |
18
0.34 IPS |