calculate_output_dim

behavenet.models.ae_model_architecture_generator.calculate_output_dim(input_dim, kernel, stride, padding_type, layer_type)

Calculate output dimension of a layer/dimension based on input size, kernel size, etc.

Inspired by:

• https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/framework/ common_shape_fns.cc#L21

• https://github.com/pytorch/pytorch/issues/3867

Parameters:

• input_dim (int) – single spatial dimension

• kernel (int) – kernel size

• stride (int) – stride length

• padding_type (str) – ‘same’ | ‘valid’

• layer_type (str) – ‘conv’ | ‘maxpool’

Returns:

• output dim (int)

• before pad (int)

• after pad (int)

Return type:

tuple