52-Concept of padding in Convolutional Neural Network(CNN)

Описание к видео 52-Concept of padding in Convolutional Neural Network(CNN)

The padding parameter of the Keras Conv2D class can take one of two values: ‘valid’ or ‘same’.
Setting the value to “valid” parameter means that the input volume is not zero-padded and the spatial dimensions are allowed to reduce via the natural application of convolution.
You can instead preserve spatial dimensions of the volume such that the output volume size matches the input volume size, by setting the value to the “same”.

Комментарии

Информация по комментариям в разработке