Upload Date | July 18 2024 02:52 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 24040RN64Y |
Model ID | Xiaomi 24040RN64Y |
Motherboard | moon |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 5.54 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
155
29.0 IPS |
|
Image Classification (F16)
|
100% |
160
30.0 IPS |
|
Image Classification (I8)
|
97% |
327
61.1 IPS |
|
Image Segmentation (F32)
|
100% |
236
3.95 IPS |
|
Image Segmentation (F16)
|
100% |
235
3.93 IPS |
|
Image Segmentation (I8)
|
98% |
305
5.09 IPS |
|
Pose Estimation (F32)
|
100% |
298
0.36 IPS |
|
Pose Estimation (F16)
|
100% |
289
0.35 IPS |
|
Pose Estimation (I8)
|
100% |
1334
1.62 IPS |
|
Object Detection (F32)
|
100% |
176
13.2 IPS |
|
Object Detection (F16)
|
100% |
176
13.2 IPS |
|
Object Detection (I8)
|
61% |
338
25.2 IPS |
|
Face Detection (F32)
|
100% |
371
4.41 IPS |
|
Face Detection (F16)
|
100% |
368
4.38 IPS |
|
Face Detection (I8)
|
86% |
750
8.91 IPS |
|
Depth Estimation (F32)
|
100% |
332
2.57 IPS |
|
Depth Estimation (F16)
|
100% |
326
2.53 IPS |
|
Depth Estimation (I8)
|
95% |
730
5.66 IPS |
|
Style Transfer (F32)
|
100% |
535
0.70 IPS |
|
Style Transfer (F16)
|
100% |
537
0.71 IPS |
|
Style Transfer (I8)
|
98% |
1396
1.84 IPS |
|
Image Super-Resolution (F32)
|
100% |
169
6.02 IPS |
|
Image Super-Resolution (F16)
|
100% |
176
6.29 IPS |
|
Image Super-Resolution (I8)
|
98% |
530
18.9 IPS |
|
Text Classification (F32)
|
100% |
174
249.4 IPS |
|
Text Classification (F16)
|
100% |
199
285.3 IPS |
|
Text Classification (I8)
|
92% |
133
191.3 IPS |
|
Machine Translation (F32)
|
100% |
389
7.15 IPS |
|
Machine Translation (F16)
|
100% |
335
6.16 IPS |
|
Machine Translation (I8)
|
64% |
184
3.38 IPS |