def _forward_pass(self, activations, with_output_activation=True):
"""Perform a forward pass on the network by computing the values
of the neurons in the hidden layers and the output layer.
Parameters
----------
activations: list, length = n_layers - 1
The ith index of the list holds the values of the ith layer.
with_output_activation : bool, default True
If True, the output passes through the output activation
function, which is either the softmax function or the
logistic function
"""
# Iterate over the hidden layers
for i in range(self.n_layers_ - 1):
activations[i + 1] = safe_sparse_dot(activations[i],
self.layers_coef_[i])
activations[i + 1] += self.layers_intercept_[i]
# For the hidden layers
if i + 1 != self.n_layers_ - 1:
hidden_activation = ACTIVATIONS[self.activation]
activations[i + 1] = hidden_activation(activations[i + 1])
# For the last layer
if with_output_activation:
output_activation = ACTIVATIONS[self.out_activation_]
activations[i + 1] = output_activation(activations[i + 1])
return activations
评论列表
文章目录
