Upload Date | December 27 2024 11:32 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | realme RMX3311 |
Model ID | realme RMX3311 |
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% |
390
72.5 IPS |
|
Image Classification (HP)
|
100% |
392
72.9 IPS |
|
Image Classification (Q)
|
97% |
350
65.4 IPS |
|
Image Segmentation (SP)
|
100% |
227
3.69 IPS |
|
Image Segmentation (HP)
|
100% |
225
3.65 IPS |
|
Image Segmentation (Q)
|
98% |
219
3.56 IPS |
|
Pose Estimation (SP)
|
100% |
737
0.86 IPS |
|
Pose Estimation (HP)
|
100% |
397
0.46 IPS |
|
Pose Estimation (Q)
|
95% |
398
0.47 IPS |
|
Object Detection (SP)
|
100% |
225
17.8 IPS |
|
Object Detection (HP)
|
100% |
195
15.5 IPS |
|
Object Detection (Q)
|
89% |
193
15.4 IPS |
|
Face Detection (SP)
|
100% |
1056
12.5 IPS |
|
Face Detection (HP)
|
100% |
963
11.4 IPS |
|
Face Detection (Q)
|
97% |
977
11.7 IPS |
|
Depth Estimation (SP)
|
100% |
982
7.56 IPS |
|
Depth Estimation (HP)
|
99% |
1197
9.25 IPS |
|
Depth Estimation (Q)
|
62% |
981
9.28 IPS |
|
Style Transfer (SP)
|
100% |
2160
2.78 IPS |
|
Style Transfer (HP)
|
100% |
3687
4.74 IPS |
|
Style Transfer (Q)
|
98% |
3630
4.68 IPS |
|
Image Super-Resolution (SP)
|
100% |
452
16.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
469
17.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
444
16.5 IPS |
|
Text Classification (SP)
|
100% |
50
66.9 IPS |
|
Text Classification (HP)
|
100% |
51
68.1 IPS |
|
Text Classification (Q)
|
91% |
96
128.6 IPS |
|
Machine Translation (SP)
|
100% |
84
1.44 IPS |
|
Machine Translation (HP)
|
100% |
84
1.45 IPS |
|
Machine Translation (Q)
|
57% |
72
1.76 IPS |