Upload Date | May 10 2025 01:00 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
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 | 10.90 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1097
204.0 IPS |
|
Image Classification (HP)
|
100% |
1270
236.1 IPS |
|
Image Classification (Q)
|
100% |
2279
423.9 IPS |
|
Image Segmentation (SP)
|
100% |
1597
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
1585
25.7 IPS |
|
Image Segmentation (Q)
|
98% |
3246
52.8 IPS |
|
Pose Estimation (SP)
|
100% |
3740
4.36 IPS |
|
Pose Estimation (HP)
|
100% |
3675
4.29 IPS |
|
Pose Estimation (Q)
|
84% |
9708
11.5 IPS |
|
Object Detection (SP)
|
98% |
1150
91.5 IPS |
|
Object Detection (HP)
|
98% |
1161
92.4 IPS |
|
Object Detection (Q)
|
83% |
2631
212.5 IPS |
|
Face Detection (SP)
|
100% |
3241
38.5 IPS |
|
Face Detection (HP)
|
100% |
3294
39.1 IPS |
|
Face Detection (Q)
|
95% |
6348
75.8 IPS |
|
Depth Estimation (SP)
|
99% |
3136
24.2 IPS |
|
Depth Estimation (HP)
|
99% |
3165
24.5 IPS |
|
Depth Estimation (Q)
|
64% |
7084
64.9 IPS |
|
Style Transfer (SP)
|
89% |
8145
10.6 IPS |
|
Style Transfer (HP)
|
89% |
8027
10.4 IPS |
|
Style Transfer (Q)
|
98% |
16258
21.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
1368
50.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
1382
51.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
2669
98.9 IPS |
|
Text Classification (SP)
|
100% |
496
661.9 IPS |
|
Text Classification (HP)
|
99% |
510
680.5 IPS |
|
Text Classification (Q)
|
88% |
496
668.4 IPS |
|
Machine Translation (SP)
|
100% |
1011
17.4 IPS |
|
Machine Translation (HP)
|
100% |
1049
18.1 IPS |
|
Machine Translation (Q)
|
50% |
395
14.0 IPS |