Upload Date | July 27 2024 07:11 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | realme RMX3853 |
Model ID | realme RMX3853 |
Motherboard | pineapple |
Governor | uag |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
Base Frequency | 1.90 GHz |
Cluster 1 | 3 Cores @ 1.90 GHz |
Cluster 2 | 4 Cores @ 2.61 GHz |
Cluster 3 | 1 Core @ 2.80 GHz |
Memory Information | |
---|---|
Size | 7.15 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
506
94.8 IPS |
|
Image Classification (F16)
|
100% |
508
95.2 IPS |
|
Image Classification (I8)
|
99% |
481
90.0 IPS |
|
Image Segmentation (F32)
|
100% |
575
9.60 IPS |
|
Image Segmentation (F16)
|
100% |
943
15.7 IPS |
|
Image Segmentation (I8)
|
98% |
811
13.5 IPS |
|
Pose Estimation (F32)
|
100% |
751
0.91 IPS |
|
Pose Estimation (F16)
|
100% |
1324
1.60 IPS |
|
Pose Estimation (I8)
|
100% |
1309
1.59 IPS |
|
Object Detection (F32)
|
100% |
197
14.7 IPS |
|
Object Detection (F16)
|
100% |
187
13.9 IPS |
|
Object Detection (I8)
|
62% |
189
14.1 IPS |
|
Face Detection (F32)
|
100% |
1425
16.9 IPS |
|
Face Detection (F16)
|
97% |
1640
19.5 IPS |
|
Face Detection (I8)
|
86% |
1558
18.5 IPS |
|
Depth Estimation (F32)
|
100% |
1109
8.60 IPS |
|
Depth Estimation (F16)
|
100% |
1972
15.3 IPS |
|
Depth Estimation (I8)
|
95% |
1903
14.8 IPS |
|
Style Transfer (F32)
|
100% |
3561
4.68 IPS |
|
Style Transfer (F16)
|
100% |
4610
6.06 IPS |
|
Style Transfer (I8)
|
98% |
4745
6.24 IPS |
|
Image Super-Resolution (F32)
|
100% |
460
16.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
558
19.9 IPS |
|
Image Super-Resolution (I8)
|
98% |
752
26.8 IPS |
|
Text Classification (F32)
|
100% |
142
203.4 IPS |
|
Text Classification (F16)
|
100% |
221
317.0 IPS |
|
Text Classification (I8)
|
92% |
240
345.6 IPS |
|
Machine Translation (F32)
|
100% |
282
5.18 IPS |
|
Machine Translation (F16)
|
100% |
606
11.1 IPS |
|
Machine Translation (I8)
|
64% |
311
5.73 IPS |