Home
last modified time | relevance | path

Searched refs:hard_sigmoid (Results 1 – 3 of 3) sorted by relevance

/external/tensorflow/tensorflow/python/keras/
Dactivations.py433 def hard_sigmoid(x): function
457 return backend.hard_sigmoid(x)
Dbackend.py5073 def hard_sigmoid(x): function
/external/tensorflow/
DRELEASE.md6665 recurrent activation function for GRU from `hard_sigmoid` to `sigmoid`, and
6667 `hard_sigmoid` since it is fast than 'sigmoid'. With new unified backend
6674 GRU(recurrent_activation='hard_sigmoid', reset_after=False) to fallback to
7314 default recurrent activation function for GRU from 'hard_sigmoid' to
7316 activation is 'hard_sigmoid' since it is fast than 'sigmoid'. With new
7324 GRU(recurrent_activation='hard_sigmoid', reset_after=False) to fallback
7535 'hard_sigmoid' to 'sigmoid' in 2.0. Historically recurrent activation is
7536 'hard_sigmoid' since it is fast than 'sigmoid'. With new unified backend
7543 construct the layer with LSTM(recurrent_activation='hard_sigmoid') to