User | LinFengJun |
Upload Date | August 18 2024 02:22 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi 9 |
Model ID | Xiaomi M2004J19C |
Motherboard | lancelot |
CPU Information | |
---|---|
Name | ARM MT6769T |
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 | 3.61 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
172
32.2 IPS |
|
Image Classification (F16)
|
100% |
178
33.3 IPS |
|
Image Classification (I8)
|
97% |
391
73.1 IPS |
|
Image Segmentation (F32)
|
100% |
229
3.83 IPS |
|
Image Segmentation (F16)
|
100% |
226
3.78 IPS |
|
Image Segmentation (I8)
|
98% |
297
4.96 IPS |
|
Pose Estimation (F32)
|
100% |
300
0.36 IPS |
|
Pose Estimation (F16)
|
100% |
304
0.37 IPS |
|
Pose Estimation (I8)
|
100% |
1438
1.74 IPS |
|
Object Detection (F32)
|
100% |
195
14.5 IPS |
|
Object Detection (F16)
|
100% |
182
13.6 IPS |
|
Object Detection (I8)
|
61% |
440
32.8 IPS |
|
Face Detection (F32)
|
100% |
368
4.37 IPS |
|
Face Detection (F16)
|
100% |
363
4.31 IPS |
|
Face Detection (I8)
|
86% |
806
9.58 IPS |
|
Depth Estimation (F32)
|
100% |
384
2.98 IPS |
|
Depth Estimation (F16)
|
100% |
314
2.43 IPS |
|
Depth Estimation (I8)
|
95% |
822
6.37 IPS |
|
Style Transfer (F32)
|
100% |
503
0.66 IPS |
|
Style Transfer (F16)
|
100% |
501
0.66 IPS |
|
Style Transfer (I8)
|
98% |
1419
1.87 IPS |
|
Image Super-Resolution (F32)
|
100% |
224
7.99 IPS |
|
Image Super-Resolution (F16)
|
100% |
228
8.15 IPS |
|
Image Super-Resolution (I8)
|
98% |
635
22.7 IPS |
|
Text Classification (F32)
|
100% |
225
323.6 IPS |
|
Text Classification (F16)
|
100% |
270
388.3 IPS |
|
Text Classification (I8)
|
92% |
219
314.9 IPS |
|
Machine Translation (F32)
|
100% |
345
6.35 IPS |
|
Machine Translation (F16)
|
100% |
359
6.60 IPS |
|
Machine Translation (I8)
|
64% |
200
3.68 IPS |