| User | hisyho |
| Upload Date | July 24 2025 12:30 PM |
| Views | 14 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Qualcomm Qualcomm |
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Sony NW-A300Series |
| Model ID | Sony NW-A300Series |
| Motherboard | icx1301 |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 10 part 2049 revision 4 |
| Base Frequency | 2.02 GHz |
| Cluster 1 | 4 Cores @ 2.02 GHz |
| Memory Information | |
|---|---|
| Size | 3.65 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
29
5.39 IPS |
|
|
Image Classification (HP)
|
0
|
||
|
Image Classification (Q)
|
0
|
||
|
Image Segmentation (SP)
|
100% |
42
0.68 IPS |
|
|
Image Segmentation (HP)
|
0
|
||
|
Image Segmentation (Q)
|
0
|
||
|
Pose Estimation (SP)
|
100% |
138
0.16 IPS |
|
|
Pose Estimation (HP)
|
99% |
249
0.29 IPS |
|
|
Pose Estimation (Q)
|
97% |
246
0.29 IPS |
|
|
Object Detection (SP)
|
100% |
24
1.93 IPS |
|
|
Object Detection (HP)
|
99% |
31
2.47 IPS |
|
|
Object Detection (Q)
|
85% |
29
2.37 IPS |
|
|
Face Detection (SP)
|
100% |
89
1.05 IPS |
|
|
Face Detection (HP)
|
100% |
73
0.87 IPS |
|
|
Face Detection (Q)
|
97% |
66
0.78 IPS |
|
|
Depth Estimation (SP)
|
100% |
97
0.74 IPS |
|
|
Depth Estimation (HP)
|
98% |
139
1.07 IPS |
|
|
Depth Estimation (Q)
|
65% |
105
0.94 IPS |
|
|
Style Transfer (SP)
|
100% |
228
0.29 IPS |
|
|
Style Transfer (HP)
|
100% |
357
0.46 IPS |
|
|
Style Transfer (Q)
|
98% |
324
0.42 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
38
1.39 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
58
2.16 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
47
1.76 IPS |
|
|
Text Classification (SP)
|
35% |
2
17.3 IPS |
|
|
Text Classification (HP)
|
35% |
4
33.4 IPS |
|
|
Text Classification (Q)
|
35% |
3
31.8 IPS |
|
|
Machine Translation (SP)
|
100% |
36
0.61 IPS |
|
|
Machine Translation (HP)
|
97% |
66
1.13 IPS |
|
|
Machine Translation (Q)
|
64% |
53
1.09 IPS |