Upload Date | July 18 2024 12:33 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | realme RMX3869 |
Model ID | realme RMX3869 |
Motherboard | RM6877 |
CPU Information | |
---|---|
Name | ARM MT6877V/TTZA |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.60 GHz |
Memory Information | |
---|---|
Size | 7.36 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
191
35.8 IPS |
|
Image Classification (F16)
|
100% |
193
36.2 IPS |
|
Image Classification (I8)
|
97% |
407
76.2 IPS |
|
Image Segmentation (F32)
|
100% |
313
5.22 IPS |
|
Image Segmentation (F16)
|
100% |
315
5.26 IPS |
|
Image Segmentation (I8)
|
98% |
504
8.41 IPS |
|
Pose Estimation (F32)
|
100% |
442
0.53 IPS |
|
Pose Estimation (F16)
|
100% |
443
0.54 IPS |
|
Pose Estimation (I8)
|
100% |
1950
2.36 IPS |
|
Object Detection (F32)
|
100% |
219
16.3 IPS |
|
Object Detection (F16)
|
100% |
139
10.4 IPS |
|
Object Detection (I8)
|
61% |
554
41.4 IPS |
|
Face Detection (F32)
|
100% |
464
5.52 IPS |
|
Face Detection (F16)
|
100% |
469
5.58 IPS |
|
Face Detection (I8)
|
86% |
1056
12.6 IPS |
|
Depth Estimation (F32)
|
100% |
479
3.71 IPS |
|
Depth Estimation (F16)
|
100% |
420
3.25 IPS |
|
Depth Estimation (I8)
|
95% |
1078
8.36 IPS |
|
Style Transfer (F32)
|
100% |
757
1.00 IPS |
|
Style Transfer (F16)
|
100% |
775
1.02 IPS |
|
Style Transfer (I8)
|
98% |
2116
2.78 IPS |
|
Image Super-Resolution (F32)
|
100% |
214
7.64 IPS |
|
Image Super-Resolution (F16)
|
100% |
252
9.01 IPS |
|
Image Super-Resolution (I8)
|
98% |
697
24.9 IPS |
|
Text Classification (F32)
|
100% |
262
376.2 IPS |
|
Text Classification (F16)
|
100% |
263
378.5 IPS |
|
Text Classification (I8)
|
92% |
215
308.5 IPS |
|
Machine Translation (F32)
|
100% |
495
9.10 IPS |
|
Machine Translation (F16)
|
100% |
483
8.89 IPS |
|
Machine Translation (I8)
|
64% |
353
6.49 IPS |