rand_embedding_cnn = WordEmbeddingCNN(
rand_seed=seed,
verbose=verbose,
optimizers=config['optimizers'],
input_dim=feature_encoder.vocabulary_size + 1,
word_embedding_dim=config['word_embedding_dim'],
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((train_X_feature, train_y),
(test_X_feature, test_y))
# 保存模型
rand_embedding_cnn.save_model(model_file_path)
else:
# 从保存的pickle中加载模型
rand_embedding_cnn.model_from_pickle(model_file_path)
# -------------- code start : 结束 -------------
if verbose > 2:
logging.debug('-' * 20)
print '-' * 20
l2_conv_filter_type= [
[layer2, 3, 1, 'valid', [2, 1], 0.25]
],
full_connected_layer_units=[[hidden1,0.5],[hidden2,0.5]],
embedding_dropout_rate=0.,
nb_epoch=30,
earlyStoping_patience=config['earlyStoping_patience'],
lr = config['lr'],
batch_size = batch_size,
embedding_weight_trainable = True,
embedding_init_weight=init_weight,
)
print (w2v_embedding_cnn.embedding_layer_output.get_weights()[0][1])
w2v_embedding_cnn.print_model_descibe()
print('+'*80)
# 训练模型
train_loss, train_accuracy, val_loss, val_accuracy = w2v_embedding_cnn.fit((train_X_feature, train_y),
(test_X_feature, test_y))
print (w2v_embedding_cnn.embedding_layer_output.get_weights()[0][1])
print('dev:%f,%f' % (train_loss, train_accuracy))
print('val:%f,%f' % (val_loss, val_accuracy))
quit()
# train
# w2v_embedding_cnn.accuracy((train_X_feature, train_y))
end_time = timeit.default_timer()
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))
# 保存模型
rand_embedding_cnn.save_model(model_file_path)
else:
# 从保存的pickle中加载模型
rand_embedding_cnn.model_from_pickle(model_file_path)
# -------------- code start : 结束 -------------
if verbose > 2:
logging.debug('-' * 20)
print '-' * 20
