Python miscc.config.cfg.RNN_TYPE Examples

The following are 6 code examples of miscc.config.cfg.RNN_TYPE(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module miscc.config.cfg , or try the search function .
Example #1
Source File: model.py    From DM-GAN with MIT License 6 votes vote down vote up 
def __init__(self, ntoken, ninput=300, drop_prob=0.5,
                 nhidden=128, nlayers=1, bidirectional=True):
        super(RNN_ENCODER, self).__init__()
        self.n_steps = cfg.TEXT.WORDS_NUM
        self.ntoken = ntoken  # size of the dictionary
        self.ninput = ninput  # size of each embedding vector
        self.drop_prob = drop_prob  # probability of an element to be zeroed
        self.nlayers = nlayers  # Number of recurrent layers
        self.bidirectional = bidirectional
        self.rnn_type = cfg.RNN_TYPE
        if bidirectional:
            self.num_directions = 2
        else:
            self.num_directions = 1
        # number of features in the hidden state
        self.nhidden = nhidden // self.num_directions

        self.define_module()
        self.init_weights()
Example #2
Source File: model.py    From multiple-objects-gan with MIT License 6 votes vote down vote up 
def __init__(self, ntoken, ninput=300, drop_prob=0.5,
                 nhidden=128, nlayers=1, bidirectional=True):
        super(RNN_ENCODER, self).__init__()
        self.n_steps = cfg.TEXT.WORDS_NUM
        self.ntoken = ntoken  # size of the dictionary
        self.ninput = ninput  # size of each embedding vector
        self.drop_prob = drop_prob  # probability of an element to be zeroed
        self.nlayers = nlayers  # Number of recurrent layers
        self.bidirectional = bidirectional
        self.rnn_type = cfg.RNN_TYPE
        if bidirectional:
            self.num_directions = 2
        else:
            self.num_directions = 1
        # number of features in the hidden state
        self.nhidden = nhidden // self.num_directions

        self.define_module()
        self.init_weights()
Example #3
Source File: model.py    From attn-gan with MIT License 6 votes vote down vote up 
def __init__(self, ntoken, ninput=300, drop_prob=0.5,
                 nhidden=128, nlayers=1, bidirectional=True):
        super(RNN_ENCODER, self).__init__()
        self.n_steps = cfg.TEXT.WORDS_NUM
        self.ntoken = ntoken  # size of the dictionary
        self.ninput = ninput  # size of each embedding vector
        self.drop_prob = drop_prob  # probability of an element to be zeroed
        self.nlayers = nlayers  # Number of recurrent layers
        self.bidirectional = bidirectional
        self.rnn_type = cfg.RNN_TYPE
        if bidirectional:
            self.num_directions = 2
        else:
            self.num_directions = 1
        # number of features in the hidden state
        self.nhidden = nhidden // self.num_directions

        self.define_module()
        self.init_weights()
Example #4
Source File: model.py    From semantic-object-accuracy-for-generative-text-to-image-synthesis with MIT License 6 votes vote down vote up 
def __init__(self, ntoken, ninput=300, drop_prob=0.5,
                 nhidden=128, nlayers=1, bidirectional=True):
        super(RNN_ENCODER, self).__init__()
        self.n_steps = cfg.TEXT.WORDS_NUM
        self.ntoken = ntoken  # size of the dictionary
        self.ninput = ninput  # size of each embedding vector
        self.drop_prob = drop_prob  # probability of an element to be zeroed
        self.nlayers = nlayers  # Number of recurrent layers
        self.bidirectional = bidirectional
        self.rnn_type = cfg.RNN_TYPE
        if bidirectional:
            self.num_directions = 2
        else:
            self.num_directions = 1
        # number of features in the hidden state
        self.nhidden = nhidden // self.num_directions

        self.define_module()
        self.init_weights()
Example #5
Source File: model.py    From AttnGAN with MIT License 6 votes vote down vote up 
def __init__(self, ntoken, ninput=300, drop_prob=0.5,
                 nhidden=128, nlayers=1, bidirectional=True):
        super(RNN_ENCODER, self).__init__()
        self.n_steps = cfg.TEXT.WORDS_NUM
        self.ntoken = ntoken  # size of the dictionary
        self.ninput = ninput  # size of each embedding vector
        self.drop_prob = drop_prob  # probability of an element to be zeroed
        self.nlayers = nlayers  # Number of recurrent layers
        self.bidirectional = bidirectional
        self.rnn_type = cfg.RNN_TYPE
        if bidirectional:
            self.num_directions = 2
        else:
            self.num_directions = 1
        # number of features in the hidden state
        self.nhidden = nhidden // self.num_directions

        self.define_module()
        self.init_weights()
Example #6
Source File: model.py    From AttnGAN with MIT License 6 votes vote down vote up 
def __init__(self, ntoken, ninput=300, drop_prob=0.5,
                 nhidden=128, nlayers=1, bidirectional=True):
        super(RNN_ENCODER, self).__init__()

        self.n_steps = cfg.TEXT.WORDS_NUM
        self.rnn_type = cfg.RNN_TYPE

        self.ntoken = ntoken  # size of the dictionary
        self.ninput = ninput  # size of each embedding vector
        self.drop_prob = drop_prob  # probability of an element to be zeroed
        self.nlayers = nlayers  # Number of recurrent layers
        self.bidirectional = bidirectional
        
        if bidirectional:
            self.num_directions = 2
        else:
            self.num_directions = 1
        # number of features in the hidden state
        self.nhidden = nhidden // self.num_directions

        self.define_module()
        self.init_weights()