User | rennsport |
Upload Date | March 12 2025 11:58 AM |
Views | 35 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | nubia NX789J |
Model ID | nubia NX789J |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 14.80 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
417
77.5 IPS |
|
Image Classification (HP)
|
100% |
21445
3.99 KIPS |
|
Image Classification (Q)
|
97% |
50342
9.39 KIPS |
|
Image Segmentation (SP)
|
100% |
553
8.96 IPS |
|
Image Segmentation (HP)
|
100% |
14635
237.2 IPS |
|
Image Segmentation (Q)
|
98% |
43072
700.4 IPS |
|
Pose Estimation (SP)
|
100% |
729
0.85 IPS |
|
Pose Estimation (HP)
|
100% |
123759
144.4 IPS |
|
Pose Estimation (Q)
|
98% |
479572
561.3 IPS |
|
Object Detection (SP)
|
100% |
417
33.0 IPS |
|
Object Detection (HP)
|
100% |
20054
1.59 KIPS |
|
Object Detection (Q)
|
85% |
23648
1.90 KIPS |
|
Face Detection (SP)
|
100% |
1063
12.6 IPS |
|
Face Detection (HP)
|
100% |
45163
536.6 IPS |
|
Face Detection (Q)
|
97% |
159765
1.91 KIPS |
|
Depth Estimation (SP)
|
100% |
921
7.09 IPS |
|
Depth Estimation (HP)
|
99% |
85011
655.0 IPS |
|
Depth Estimation (Q)
|
63% |
149091
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
1566
2.01 IPS |
|
Style Transfer (HP)
|
98% |
99045
127.7 IPS |
|
Style Transfer (Q)
|
98% |
496611
640.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
492
18.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
55099
2.03 KIPS |
|
Image Super-Resolution (Q)
|
97% |
135231
5.01 KIPS |
|
Text Classification (SP)
|
100% |
616
822.1 IPS |
|
Text Classification (HP)
|
100% |
3939
5.26 KIPS |
|
Text Classification (Q)
|
93% |
8181
11.0 KIPS |
|
Machine Translation (SP)
|
100% |
1053
18.1 IPS |
|
Machine Translation (HP)
|
100% |
4787
82.5 IPS |
|
Machine Translation (Q)
|
56% |
3334
85.9 IPS |