Upload Date | December 27 2024 08:40 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | HONOR BRP-NX1M |
Model ID | HONOR BRP-NX1M |
Motherboard | parrot |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
429
79.7 IPS |
|
Image Classification (HP)
|
100% |
430
79.9 IPS |
|
Image Classification (Q)
|
100% |
1345
250.0 IPS |
|
Image Segmentation (SP)
|
100% |
507
8.22 IPS |
|
Image Segmentation (HP)
|
100% |
500
8.11 IPS |
|
Image Segmentation (Q)
|
98% |
1549
25.2 IPS |
|
Pose Estimation (SP)
|
100% |
1943
2.27 IPS |
|
Pose Estimation (HP)
|
100% |
623
0.73 IPS |
|
Pose Estimation (Q)
|
84% |
1169
1.39 IPS |
|
Object Detection (SP)
|
100% |
136
10.8 IPS |
|
Object Detection (HP)
|
100% |
136
10.8 IPS |
|
Object Detection (Q)
|
83% |
392
31.7 IPS |
|
Face Detection (SP)
|
100% |
345
4.10 IPS |
|
Face Detection (HP)
|
100% |
342
4.06 IPS |
|
Face Detection (Q)
|
95% |
800
9.55 IPS |
|
Depth Estimation (SP)
|
100% |
494
3.80 IPS |
|
Depth Estimation (HP)
|
99% |
494
3.81 IPS |
|
Depth Estimation (Q)
|
64% |
1001
9.17 IPS |
|
Style Transfer (SP)
|
89% |
1133
1.47 IPS |
|
Style Transfer (HP)
|
89% |
1124
1.46 IPS |
|
Style Transfer (Q)
|
98% |
2475
3.19 IPS |
|
Image Super-Resolution (SP)
|
100% |
248
9.15 IPS |
|
Image Super-Resolution (HP)
|
100% |
260
9.61 IPS |
|
Image Super-Resolution (Q)
|
97% |
616
22.8 IPS |
|
Text Classification (SP)
|
100% |
155
207.1 IPS |
|
Text Classification (HP)
|
100% |
155
206.2 IPS |
|
Text Classification (Q)
|
88% |
257
346.3 IPS |
|
Machine Translation (SP)
|
100% |
263
4.52 IPS |
|
Machine Translation (HP)
|
100% |
258
4.44 IPS |
|
Machine Translation (Q)
|
50% |
168
5.98 IPS |