Upload Date | April 25 2024 12:02 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Realme 7 |
Model ID | realme RMX2151 |
Motherboard | RM6785 |
CPU Information | |
---|---|
Name | ARM MT6785V/CD |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.05 GHz |
Memory Information | |
---|---|
Size | 5.50 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
177
33.2 IPS |
|
Image Classification (F16)
|
100% |
176
32.9 IPS |
|
Image Classification (I8)
|
97% |
282
52.7 IPS |
|
Image Segmentation (F32)
|
100% |
278
4.64 IPS |
|
Image Segmentation (F16)
|
100% |
273
4.57 IPS |
|
Image Segmentation (I8)
|
98% |
388
6.47 IPS |
|
Pose Estimation (F32)
|
100% |
344
0.42 IPS |
|
Pose Estimation (F16)
|
100% |
343
0.42 IPS |
|
Pose Estimation (I8)
|
100% |
1624
1.97 IPS |
|
Object Detection (F32)
|
100% |
185
13.8 IPS |
|
Object Detection (F16)
|
100% |
209
15.6 IPS |
|
Object Detection (I8)
|
61% |
389
29.1 IPS |
|
Face Detection (F32)
|
100% |
404
4.80 IPS |
|
Face Detection (F16)
|
100% |
395
4.70 IPS |
|
Face Detection (I8)
|
86% |
725
8.62 IPS |
|
Depth Estimation (F32)
|
100% |
378
2.93 IPS |
|
Depth Estimation (F16)
|
100% |
376
2.91 IPS |
|
Depth Estimation (I8)
|
95% |
812
6.30 IPS |
|
Style Transfer (F32)
|
100% |
603
0.79 IPS |
|
Style Transfer (F16)
|
100% |
598
0.79 IPS |
|
Style Transfer (I8)
|
98% |
1864
2.45 IPS |
|
Image Super-Resolution (F32)
|
100% |
232
8.30 IPS |
|
Image Super-Resolution (F16)
|
100% |
230
8.22 IPS |
|
Image Super-Resolution (I8)
|
98% |
748
26.7 IPS |
|
Text Classification (F32)
|
100% |
237
340.1 IPS |
|
Text Classification (F16)
|
100% |
270
388.0 IPS |
|
Text Classification (I8)
|
92% |
191
274.7 IPS |
|
Machine Translation (F32)
|
100% |
389
7.17 IPS |
|
Machine Translation (F16)
|
100% |
388
7.14 IPS |
|
Machine Translation (I8)
|
64% |
296
5.44 IPS |