Upload Date | December 27 2024 07:25 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | realme RMX3312 |
Model ID | realme RMX3312 |
Motherboard | lahaina |
Governor | uag |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 10.99 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
405
75.3 IPS |
|
Image Classification (HP)
|
100% |
421
78.3 IPS |
|
Image Classification (Q)
|
100% |
1147
213.2 IPS |
|
Image Segmentation (SP)
|
100% |
424
6.88 IPS |
|
Image Segmentation (HP)
|
100% |
376
6.10 IPS |
|
Image Segmentation (Q)
|
98% |
1091
17.7 IPS |
|
Pose Estimation (SP)
|
100% |
1683
1.96 IPS |
|
Pose Estimation (HP)
|
100% |
1711
2.00 IPS |
|
Pose Estimation (Q)
|
84% |
2749
3.26 IPS |
|
Object Detection (SP)
|
100% |
391
31.0 IPS |
|
Object Detection (HP)
|
100% |
383
30.4 IPS |
|
Object Detection (Q)
|
83% |
1121
90.6 IPS |
|
Face Detection (SP)
|
100% |
1256
14.9 IPS |
|
Face Detection (HP)
|
100% |
1246
14.8 IPS |
|
Face Detection (Q)
|
95% |
2625
31.3 IPS |
|
Depth Estimation (SP)
|
100% |
1651
12.7 IPS |
|
Depth Estimation (HP)
|
99% |
1546
11.9 IPS |
|
Depth Estimation (Q)
|
64% |
2282
20.9 IPS |
|
Style Transfer (SP)
|
89% |
2893
3.76 IPS |
|
Style Transfer (HP)
|
89% |
2879
3.74 IPS |
|
Style Transfer (Q)
|
98% |
5722
7.38 IPS |
|
Image Super-Resolution (SP)
|
100% |
867
32.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
864
31.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
625
23.2 IPS |
|
Text Classification (SP)
|
100% |
167
222.5 IPS |
|
Text Classification (HP)
|
100% |
169
225.4 IPS |
|
Text Classification (Q)
|
88% |
276
372.3 IPS |
|
Machine Translation (SP)
|
100% |
242
4.16 IPS |
|
Machine Translation (HP)
|
100% |
240
4.13 IPS |
|
Machine Translation (Q)
|
50% |
158
5.60 IPS |