def _initialize_from_file(self, lm_file):
weights = {}
with open(lm_file, 'rb') as f:
self._input_layer_size = pickle.load(f)
self._hidden_layer_size = pickle.load(f)
self._output_layer_size = pickle.load(f)
self.sparse_embeddings = pickle.load(f)
self.w2v_embeddings = pickle.load(f)
weights['W_xi'] = pickle.load(f)
weights['W_hi'] = pickle.load(f)
weights['W_ci'] = pickle.load(f)
weights['b_i'] = pickle.load(f)
weights['W_xf'] = pickle.load(f)
weights['W_hf'] = pickle.load(f)
weights['W_cf'] = pickle.load(f)
weights['b_f'] = pickle.load(f)
weights['W_xc'] = pickle.load(f)
weights['W_hc'] = pickle.load(f)
weights['b_c'] = pickle.load(f)
weights['W_xo'] = pickle.load(f)
weights['W_ho'] = pickle.load(f)
weights['W_co'] = pickle.load(f)
weights['b_o'] = pickle.load(f)
weights['W_hy'] = pickle.load(f)
weights['b_y'] = pickle.load(f)
self._lstm = _LSTM(self._input_layer_size,
self._hidden_layer_size,
self._output_layer_size,
weights=weights)
self.print('initialized model from file: %s' % lm_file)
def _initialize_from_file(self, lm_file):
weights = {}
with open(lm_file, 'rb') as f:
self._input_layer_size = pickle.load(f)
self._hidden_layer_size = pickle.load(f)
self._output_layer_size = pickle.load(f)
self.sparse_embeddings = pickle.load(f)
self.w2v_embeddings = pickle.load(f)
weights['W_xi'] = pickle.load(f)
weights['W_hi'] = pickle.load(f)
weights['W_ci'] = pickle.load(f)
weights['b_i'] = pickle.load(f)
weights['W_xf'] = pickle.load(f)
weights['W_hf'] = pickle.load(f)
weights['W_cf'] = pickle.load(f)
weights['b_f'] = pickle.load(f)
weights['W_xc'] = pickle.load(f)
weights['W_hc'] = pickle.load(f)
weights['b_c'] = pickle.load(f)
weights['W_xo'] = pickle.load(f)
weights['W_ho'] = pickle.load(f)
weights['W_co'] = pickle.load(f)
weights['b_o'] = pickle.load(f)
weights['W_hy'] = pickle.load(f)
weights['b_y'] = pickle.load(f)
self._lstm = _LSTM(self._input_layer_size, self._hidden_layer_size, self._output_layer_size, weights=weights)
self.print('initialized model from file: %s' % lm_file)
def _initialize(self, tokenized_sentences):
self.w2v_embeddings = Word2Vec(tokenized_sentences, size=self._input_layer_size, min_count=1)
vocab = set()
for s in tokenized_sentences:
vocab.update(s)
self.sparse_embeddings = {key: i for i, key in enumerate(vocab)}
self._output_layer_size = len(self.sparse_embeddings)
self._lstm = _LSTM(self._input_layer_size, self._hidden_layer_size, self._output_layer_size)
self.print('initialized new model')
def _initialize(self, tokenized_sentences):
self.w2v_embeddings = Word2Vec(tokenized_sentences,
size=self._input_layer_size,
min_count=1)
vocab = set()
for s in tokenized_sentences:
vocab.update(s)
self.sparse_embeddings = {key: i for i, key in enumerate(vocab)}
self._output_layer_size = len(self.sparse_embeddings)
self._lstm = _LSTM(self._input_layer_size, self._hidden_layer_size,
self._output_layer_size)
self.print('initialized new model')