Upload Date | January 02 2025 06:48 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | nubia NX733J |
Model ID | nubia NX733J |
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% |
268
49.8 IPS |
|
Image Classification (HP)
|
100% |
977
181.7 IPS |
|
Image Classification (Q)
|
100% |
2246
417.7 IPS |
|
Image Segmentation (SP)
|
100% |
1612
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
1597
25.9 IPS |
|
Image Segmentation (Q)
|
98% |
3250
52.8 IPS |
|
Pose Estimation (SP)
|
100% |
3753
4.38 IPS |
|
Pose Estimation (HP)
|
100% |
3622
4.23 IPS |
|
Pose Estimation (Q)
|
84% |
9893
11.7 IPS |
|
Object Detection (SP)
|
98% |
1166
92.8 IPS |
|
Object Detection (HP)
|
98% |
1152
91.7 IPS |
|
Object Detection (Q)
|
83% |
2643
213.5 IPS |
|
Face Detection (SP)
|
100% |
3246
38.6 IPS |
|
Face Detection (HP)
|
100% |
3244
38.5 IPS |
|
Face Detection (Q)
|
95% |
6388
76.3 IPS |
|
Depth Estimation (SP)
|
99% |
3223
24.9 IPS |
|
Depth Estimation (HP)
|
99% |
3213
24.8 IPS |
|
Depth Estimation (Q)
|
64% |
6889
63.1 IPS |
|
Style Transfer (SP)
|
89% |
7925
10.3 IPS |
|
Style Transfer (HP)
|
89% |
7015
9.11 IPS |
|
Style Transfer (Q)
|
98% |
13580
17.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
1366
50.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
1360
50.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
2951
109.4 IPS |
|
Text Classification (SP)
|
100% |
464
619.8 IPS |
|
Text Classification (HP)
|
99% |
425
567.5 IPS |
|
Text Classification (Q)
|
88% |
454
612.4 IPS |
|
Machine Translation (SP)
|
100% |
885
15.2 IPS |
|
Machine Translation (HP)
|
100% |
888
15.3 IPS |
|
Machine Translation (Q)
|
50% |
363
12.9 IPS |