MaxPool1D

neuralpy.layers.pooling.MaxPool1D(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False, name=None)
info

MaxPool1D Layer is mostly stable and can be used for any project. In the future, any chance of breaking changes is very low.

MaxPool1D Applies a 1D max pooling over an input.

To learn more about MaxPool1D layers, please check PyTorch documentation

Supported Arguments:

  • kernel_size: (Integer | Tuple) Kernel size of the layer
  • stride=None: (Integer | Tuple) Stride for the conv.
  • padding=0: (Integer | Tuple) Padding for the conv layer.
  • dilation=1: (Integer | Tuple) Controls the spacing between the kernel elements
  • return_indices=False: (Boolean) If True, will return the max indices along with the outputs.
  • ceil_mode=False: (Boolean) When True, will use ceil instead of floor to compute the output shape
  • name=None: (String) Name of the layer, if not provided then automatically calculates a unique name for the layer

Example Code

from neuralpy.models import Sequential
from neuralpy.layers.pooling import MaxPool1D
from neuralpy.layers.convolutional import Conv1D
# Making the model
model = Sequential()
model.add(Conv1D(filters=8, kernel_size=3, input_shape=(1, 28), stride=1, name="first cnn"))
model.add(MaxPool1D(kernel_size=2, stride=2, padding=0, dilation=1, return_indices=False, ceil_mode=False, name="Pool Layer"))
Edit this page