User | springkim |
Upload Date | April 18 2025 06:04 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI GRL-AL10 |
Model ID | HUAWEI GRL-AL10 |
Motherboard | GRL |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 72 architecture 8 variant 2 part 3331 revision 0 |
Base Frequency | 1.55 GHz |
Cluster 1 | 4 Cores @ 1.55 GHz |
Cluster 2 | 3 Cores @ 2.18 GHz |
Cluster 3 | 1 Core @ 2.30 GHz |
Memory Information | |
---|---|
Size | 15.24 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
465
86.5 IPS |
|
Image Classification (HP)
|
100% |
491
91.3 IPS |
|
Image Classification (Q)
|
100% |
1337
248.7 IPS |
|
Image Segmentation (SP)
|
100% |
618
10.0 IPS |
|
Image Segmentation (HP)
|
100% |
623
10.1 IPS |
|
Image Segmentation (Q)
|
98% |
1435
23.3 IPS |
|
Pose Estimation (SP)
|
100% |
2125
2.48 IPS |
|
Pose Estimation (HP)
|
100% |
2146
2.50 IPS |
|
Pose Estimation (Q)
|
84% |
2901
3.44 IPS |
|
Object Detection (SP)
|
98% |
471
37.5 IPS |
|
Object Detection (HP)
|
98% |
420
33.4 IPS |
|
Object Detection (Q)
|
83% |
1186
95.8 IPS |
|
Face Detection (SP)
|
100% |
1369
16.3 IPS |
|
Face Detection (HP)
|
100% |
1366
16.2 IPS |
|
Face Detection (Q)
|
95% |
3053
36.4 IPS |
|
Depth Estimation (SP)
|
99% |
2099
16.2 IPS |
|
Depth Estimation (HP)
|
99% |
1858
14.4 IPS |
|
Depth Estimation (Q)
|
64% |
2763
25.3 IPS |
|
Style Transfer (SP)
|
89% |
3479
4.52 IPS |
|
Style Transfer (HP)
|
89% |
3322
4.31 IPS |
|
Style Transfer (Q)
|
98% |
6494
8.37 IPS |
|
Image Super-Resolution (SP)
|
100% |
1152
42.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
1134
41.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1579
58.5 IPS |
|
Text Classification (SP)
|
100% |
525
700.2 IPS |
|
Text Classification (HP)
|
99% |
546
729.1 IPS |
|
Text Classification (Q)
|
88% |
877
1.18 KIPS |
|
Machine Translation (SP)
|
100% |
756
13.0 IPS |
|
Machine Translation (HP)
|
100% |
700
12.1 IPS |
|
Machine Translation (Q)
|
50% |
411
14.6 IPS |