Upload Date | April 27 2024 04:38 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 23108RN04Y |
Model ID | Xiaomi 23108RN04Y |
Motherboard | gust |
CPU Information | |
---|---|
Name | ARM MT6769V/CZ |
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 | 7.56 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
115
21.5 IPS |
|
Image Classification (F16)
|
100% |
121
22.7 IPS |
|
Image Classification (I8)
|
97% |
242
45.2 IPS |
|
Image Segmentation (F32)
|
100% |
181
3.02 IPS |
|
Image Segmentation (F16)
|
100% |
178
2.98 IPS |
|
Image Segmentation (I8)
|
98% |
267
4.47 IPS |
|
Pose Estimation (F32)
|
100% |
250
0.30 IPS |
|
Pose Estimation (F16)
|
100% |
242
0.29 IPS |
|
Pose Estimation (I8)
|
100% |
1073
1.30 IPS |
|
Object Detection (F32)
|
100% |
123
9.15 IPS |
|
Object Detection (F16)
|
100% |
123
9.21 IPS |
|
Object Detection (I8)
|
61% |
328
24.5 IPS |
|
Face Detection (F32)
|
100% |
292
3.47 IPS |
|
Face Detection (F16)
|
100% |
303
3.60 IPS |
|
Face Detection (I8)
|
86% |
631
7.51 IPS |
|
Depth Estimation (F32)
|
100% |
280
2.17 IPS |
|
Depth Estimation (F16)
|
100% |
272
2.11 IPS |
|
Depth Estimation (I8)
|
95% |
655
5.08 IPS |
|
Style Transfer (F32)
|
100% |
478
0.63 IPS |
|
Style Transfer (F16)
|
100% |
466
0.61 IPS |
|
Style Transfer (I8)
|
98% |
1255
1.65 IPS |
|
Image Super-Resolution (F32)
|
100% |
178
6.37 IPS |
|
Image Super-Resolution (F16)
|
100% |
150
5.37 IPS |
|
Image Super-Resolution (I8)
|
98% |
564
20.1 IPS |
|
Text Classification (F32)
|
100% |
193
278.1 IPS |
|
Text Classification (F16)
|
100% |
149
213.7 IPS |
|
Text Classification (I8)
|
92% |
157
225.3 IPS |
|
Machine Translation (F32)
|
100% |
275
5.06 IPS |
|
Machine Translation (F16)
|
100% |
251
4.62 IPS |
|
Machine Translation (I8)
|
64% |
166
3.05 IPS |