# ------------------------------------------------------------------------------
model_file_path = ''.join([str(item) for item in config['model_file_path']])
word2vec_file_path = config['word2vec_model_file_path']
word2vec_file_path = word2vec_file_path%config['word_embedding_dim']
print(model_file_path)
print(word2vec_file_path)
for seed in [10,100,500,1337,2000,300]:
w2v_embedding_cnn = WordEmbeddingCNN(
rand_seed=seed,
verbose=verbose,
input_dim=feature_encoder.vocabulary_size + 1,
word_embedding_dim=config['word_embedding_dim'],
embedding_init_weight=feature_encoder.to_embedding_weight(word2vec_file_path),
input_length=config['padding_length'],
num_labels=len(label_to_index),
conv_filter_type=config['conv_filter_type'],
k=config['kmax_k'],
embedding_dropout_rate=config['embedding_dropout_rate'],
output_dropout_rate=config['output_dropout_rate'],
nb_epoch=int(config['cnn_nb_epoch']),
earlyStoping_patience=config['earlyStoping_patience'],
feature_encoder=feature_encoder.vocabulary_size+1,
optimizers='sgd',
lr= 1e-1,
batch_size = 128,
)
w2v_embedding_cnn.print_model_descibe()
test_cnn_feature_file_path = test_cnn_feature_file_path % seed
word2vec_file_path = (config['word2vec_file_path'])%config['word_embedding_dim']
print model_file_path
print result_file_path
print train_cnn_feature_file_path
print test_cnn_feature_file_path
print word2vec_file_path
rand_embedding_cnn = WordEmbeddingCNN(
rand_seed=seed,
verbose=verbose,
input_dim=feature_encoder.vocabulary_size + 1,
word_embedding_dim=config['word_embedding_dim'],
embedding_init_weight=feature_encoder.to_embedding_weight(word2vec_file_path),
input_length=config['sentence_padding_length'],
num_labels=len(label_to_index),
conv_filter_type=config['conv_filter_type'],
k=config['kmax_k'],
embedding_dropout_rate=config['embedding_dropout_rate'],
output_dropout_rate=config['output_dropout_rate'],
nb_epoch=int(config['cnn_nb_epoch']),
earlyStoping_patience=config['earlyStoping_patience'],
)
rand_embedding_cnn.print_model_descibe()
if config['refresh_all_model'] or not os.path.exists(model_file_path):
# 训练模型
rand_embedding_cnn.fit((feature_encoder.train_padding_index, train_y),
(map(feature_encoder.transform_sentence, test_X), test_y))
