Upload Date | July 19 2024 04:25 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 23129RA5FL |
Model ID | Xiaomi 23129RA5FL |
Motherboard | bengal |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
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 @ 2.80 GHz |
Memory Information | |
---|---|
Size | 5.47 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
149
27.9 IPS |
|
Image Classification (F16)
|
100% |
150
28.1 IPS |
|
Image Classification (I8)
|
97% |
242
45.2 IPS |
|
Image Segmentation (F32)
|
100% |
207
3.45 IPS |
|
Image Segmentation (F16)
|
100% |
200
3.34 IPS |
|
Image Segmentation (I8)
|
98% |
259
4.32 IPS |
|
Pose Estimation (F32)
|
100% |
284
0.34 IPS |
|
Pose Estimation (F16)
|
100% |
285
0.35 IPS |
|
Pose Estimation (I8)
|
100% |
802
0.97 IPS |
|
Object Detection (F32)
|
100% |
157
11.7 IPS |
|
Object Detection (F16)
|
100% |
156
11.6 IPS |
|
Object Detection (I8)
|
61% |
269
20.1 IPS |
|
Face Detection (F32)
|
100% |
312
3.71 IPS |
|
Face Detection (F16)
|
100% |
317
3.76 IPS |
|
Face Detection (I8)
|
86% |
549
6.53 IPS |
|
Depth Estimation (F32)
|
100% |
294
2.28 IPS |
|
Depth Estimation (F16)
|
100% |
293
2.27 IPS |
|
Depth Estimation (I8)
|
95% |
566
4.39 IPS |
|
Style Transfer (F32)
|
100% |
441
0.58 IPS |
|
Style Transfer (F16)
|
100% |
463
0.61 IPS |
|
Style Transfer (I8)
|
98% |
1152
1.52 IPS |
|
Image Super-Resolution (F32)
|
100% |
168
6.01 IPS |
|
Image Super-Resolution (F16)
|
100% |
165
5.91 IPS |
|
Image Super-Resolution (I8)
|
98% |
389
13.9 IPS |
|
Text Classification (F32)
|
100% |
193
277.6 IPS |
|
Text Classification (F16)
|
100% |
192
275.9 IPS |
|
Text Classification (I8)
|
92% |
148
212.6 IPS |
|
Machine Translation (F32)
|
100% |
324
5.96 IPS |
|
Machine Translation (F16)
|
100% |
336
6.18 IPS |
|
Machine Translation (I8)
|
64% |
194
3.56 IPS |