Research Article
Continuous Human Motion Recognition Based on FMCW Radar and Transformer
Table 1
Feature encoding layer network parameters.
| | Parameters (kernel, maps, stride) | Output(height, width, channel) |
| | Input | — | | | Convolution | | | | Max pooling | | | | Convolution | | | | Max pooling | | | | Inception 1 | | | | Max pooling | | | | Inception 2 | | | | Max pooling | | | | Inception 3 | | | | Max pooling | | |
|
|
