Upload Date | April 13 2025 06:07 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | realme RMX3709 |
Model ID | realme RMX3709 |
Motherboard | taro |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.50 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 10.95 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
162
30.1 IPS |
|
Image Classification (HP)
|
100% |
8232
1.53 KIPS |
|
Image Classification (Q)
|
99% |
23310
4.35 KIPS |
|
Image Segmentation (SP)
|
100% |
210
3.40 IPS |
|
Image Segmentation (HP)
|
100% |
6685
108.4 IPS |
|
Image Segmentation (Q)
|
98% |
19144
311.3 IPS |
|
Pose Estimation (SP)
|
100% |
285
0.33 IPS |
|
Pose Estimation (HP)
|
100% |
36653
42.8 IPS |
|
Pose Estimation (Q)
|
94% |
225460
264.3 IPS |
|
Object Detection (SP)
|
100% |
162
12.9 IPS |
|
Object Detection (HP)
|
100% |
7811
619.6 IPS |
|
Object Detection (Q)
|
88% |
11877
951.5 IPS |
|
Face Detection (SP)
|
100% |
439
5.22 IPS |
|
Face Detection (HP)
|
100% |
18155
215.7 IPS |
|
Face Detection (Q)
|
97% |
72252
861.5 IPS |
|
Depth Estimation (SP)
|
100% |
368
2.84 IPS |
|
Depth Estimation (HP)
|
99% |
28125
217.3 IPS |
|
Depth Estimation (Q)
|
64% |
66141
608.9 IPS |
|
Style Transfer (SP)
|
100% |
642
0.82 IPS |
|
Style Transfer (HP)
|
98% |
39613
51.1 IPS |
|
Style Transfer (Q)
|
98% |
227060
292.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
184
6.81 IPS |
|
Image Super-Resolution (HP)
|
100% |
21646
799.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
71694
2.66 KIPS |
|
Text Classification (SP)
|
100% |
235
314.1 IPS |
|
Text Classification (HP)
|
100% |
1897
2.53 KIPS |
|
Text Classification (Q)
|
94% |
4428
5.94 KIPS |
|
Machine Translation (SP)
|
100% |
411
7.08 IPS |
|
Machine Translation (HP)
|
100% |
2182
37.6 IPS |
|
Machine Translation (Q)
|
50% |
1233
42.7 IPS |