| Upload Date | February 05 2025 12:32 AM |
| Views | 8 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | placeholder |
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google brya |
| Model ID | Google brya |
| Motherboard | felwinter |
| CPU Information | |
|---|---|
| Name | placeholder |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 78 architecture 8 variant 2 part 0 revision 1 |
| Base Frequency | 0 MHz |
| Cluster 1 | 8 Cores |
| Memory Information | |
|---|---|
| Size | 6.83 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
122
22.7 IPS |
|
|
Image Classification (HP)
|
100% |
122
22.7 IPS |
|
|
Image Classification (Q)
|
99% |
59
11.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
143
2.31 IPS |
|
|
Image Segmentation (HP)
|
100% |
142
2.30 IPS |
|
|
Image Segmentation (Q)
|
98% |
68
1.10 IPS |
|
|
Pose Estimation (SP)
|
100% |
194
0.23 IPS |
|
|
Pose Estimation (HP)
|
100% |
195
0.23 IPS |
|
|
Pose Estimation (Q)
|
98% |
151
0.18 IPS |
|
|
Object Detection (SP)
|
100% |
114
9.07 IPS |
|
|
Object Detection (HP)
|
100% |
111
8.80 IPS |
|
|
Object Detection (Q)
|
87% |
63
5.06 IPS |
|
|
Face Detection (SP)
|
100% |
331
3.93 IPS |
|
|
Face Detection (HP)
|
100% |
328
3.90 IPS |
|
|
Face Detection (Q)
|
97% |
119
1.42 IPS |
|
|
Depth Estimation (SP)
|
100% |
263
2.02 IPS |
|
|
Depth Estimation (HP)
|
99% |
268
2.06 IPS |
|
|
Depth Estimation (Q)
|
64% |
144
1.30 IPS |
|
|
Style Transfer (SP)
|
100% |
453
0.58 IPS |
|
|
Style Transfer (HP)
|
100% |
453
0.58 IPS |
|
|
Style Transfer (Q)
|
98% |
407
0.52 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
128
4.73 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
127
4.68 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
82
3.04 IPS |
|
|
Text Classification (SP)
|
100% |
150
199.7 IPS |
|
|
Text Classification (HP)
|
100% |
151
201.5 IPS |
|
|
Text Classification (Q)
|
91% |
65
87.2 IPS |
|
|
Machine Translation (SP)
|
100% |
273
4.70 IPS |
|
|
Machine Translation (HP)
|
100% |
279
4.80 IPS |
|
|
Machine Translation (Q)
|
57% |
78
1.91 IPS |