User | y561994 |
Upload Date | September 20 2025 08:12 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI DBY-W09 |
Model ID | HUAWEI DBY-W09 |
Motherboard | DBY |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 5.57 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
259
48.2 IPS |
|
Image Classification (HP)
|
100% |
351
65.3 IPS |
|
Image Classification (Q)
|
97% |
348
65.0 IPS |
|
Image Segmentation (SP)
|
100% |
181
2.93 IPS |
|
Image Segmentation (HP)
|
100% |
239
3.87 IPS |
|
Image Segmentation (Q)
|
98% |
230
3.74 IPS |
|
Pose Estimation (SP)
|
100% |
491
0.57 IPS |
|
Pose Estimation (HP)
|
100% |
985
1.15 IPS |
|
Pose Estimation (Q)
|
95% |
945
1.11 IPS |
|
Object Detection (SP)
|
100% |
201
16.0 IPS |
|
Object Detection (HP)
|
100% |
209
16.6 IPS |
|
Object Detection (Q)
|
89% |
215
17.2 IPS |
|
Face Detection (SP)
|
100% |
636
7.56 IPS |
|
Face Detection (HP)
|
100% |
1170
13.9 IPS |
|
Face Detection (Q)
|
97% |
1137
13.6 IPS |
|
Depth Estimation (SP)
|
100% |
575
4.43 IPS |
|
Depth Estimation (HP)
|
99% |
1109
8.57 IPS |
|
Depth Estimation (Q)
|
62% |
899
8.51 IPS |
|
Style Transfer (SP)
|
100% |
1105
1.42 IPS |
|
Style Transfer (HP)
|
100% |
2860
3.68 IPS |
|
Style Transfer (Q)
|
98% |
2836
3.66 IPS |
|
Image Super-Resolution (SP)
|
100% |
262
9.69 IPS |
|
Image Super-Resolution (HP)
|
100% |
564
20.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
550
20.4 IPS |
|
Text Classification (SP)
|
100% |
50
67.3 IPS |
|
Text Classification (HP)
|
100% |
51
68.2 IPS |
|
Text Classification (Q)
|
91% |
97
129.9 IPS |
|
Machine Translation (SP)
|
100% |
87
1.50 IPS |
|
Machine Translation (HP)
|
100% |
89
1.53 IPS |
|
Machine Translation (Q)
|
57% |
78
1.90 IPS |