Research Article
Image Real-Time Detection Using LSE-Yolo Neural Network in Artificial Intelligence-Based Internet of Things for Smart Cities and Smart Homes
Table 1
The structure of darknet53.
| | Type | Filters | Size | Output |
| | Convolutional | 32 | | | | Convolutional | 64 | | | | Convolutional | 32 | | | 1× | Convolutional | 64 | | | | Residual | | | | | Convolutional | 128 | | | | Convolutional | 64 | | | 2× | Convolutional | 128 | | | | Residual | | | | | Convolutional | 256 | | | | Convolutional | 128 | | | 8× | Convolutional | 256 | | | | Residual | | | | | Convolutional | 512 | | | | Convolutional | 256 | | | 8× | Convolutional | 512 | | | | Residual | | | | | Convolutional | 1024 | | | | Convolutional | 512 | | | 4× | Convolutional | 1024 | | | | Residual | | | | | Avgpool | | Global | | | Connected | | 1000 | | | Softmax | | | |
|
|