| Upload Date | October 26 2024 10:55 AM |
| Views | 12 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | ARM Rockchip |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Blackview Tab 7 WiFi |
| Model ID | Blackview Tab 7 WiFi |
| Motherboard | rk30sdk |
| Governor | interactive |
| CPU Information | |
|---|---|
| Name | ARM Rockchip |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3332 revision 2 |
| Base Frequency | 1.51 GHz |
| Cluster 1 | 4 Cores @ 1.51 GHz |
| Memory Information | |
|---|---|
| Size | 2.89 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
31
5.69 IPS |
|
|
Image Classification (HP)
|
100% |
30
5.66 IPS |
|
|
Image Classification (Q)
|
100% |
59
10.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
43
0.70 IPS |
|
|
Image Segmentation (HP)
|
100% |
43
0.70 IPS |
|
|
Image Segmentation (Q)
|
98% |
84
1.36 IPS |
|
|
Pose Estimation (SP)
|
100% |
163
0.19 IPS |
|
|
Pose Estimation (HP)
|
100% |
161
0.19 IPS |
|
|
Pose Estimation (Q)
|
84% |
119
0.14 IPS |
|
|
Object Detection (SP)
|
100% |
30
2.42 IPS |
|
|
Object Detection (HP)
|
100% |
30
2.42 IPS |
|
|
Object Detection (Q)
|
83% |
58
4.68 IPS |
|
|
Face Detection (SP)
|
100% |
104
1.24 IPS |
|
|
Face Detection (HP)
|
100% |
104
1.24 IPS |
|
|
Face Detection (Q)
|
95% |
172
2.05 IPS |
|
|
Depth Estimation (SP)
|
100% |
144
1.11 IPS |
|
|
Depth Estimation (HP)
|
99% |
125
0.96 IPS |
|
|
Depth Estimation (Q)
|
64% |
133
1.21 IPS |
|
|
Style Transfer (SP)
|
89% |
263
0.34 IPS |
|
|
Style Transfer (HP)
|
89% |
264
0.34 IPS |
|
|
Style Transfer (Q)
|
98% |
315
0.41 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
73
2.69 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
73
2.69 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
73
2.71 IPS |
|
|
Text Classification (SP)
|
100% |
38
50.4 IPS |
|
|
Text Classification (HP)
|
100% |
37
49.8 IPS |
|
|
Text Classification (Q)
|
88% |
60
80.7 IPS |
|
|
Machine Translation (SP)
|
100% |
64
1.10 IPS |
|
|
Machine Translation (HP)
|
100% |
63
1.09 IPS |
|
|
Machine Translation (Q)
|
50% |
35
1.25 IPS |