def main(): # 加载配置文件 with open('./config.yml') as file_config: config = yaml.load(file_config) feature_names = config['model_params']['feature_names'] # 初始化embedding shape, dropouts, 预训练的embedding也在这里初始化) feature_weight_shape_dict, feature_weight_dropout_dict, \ feature_init_weight_dict = dict(), dict(), dict() for feature_name in feature_names: feature_weight_shape_dict[feature_name] = \ config['model_params']['embed_params'][feature_name]['shape'] feature_weight_dropout_dict[feature_name] = \ config['model_params']['embed_params'][feature_name]['dropout_rate'] path_pre_train = config['model_params']['embed_params'][feature_name]['path'] if path_pre_train: with open(path_pre_train, 'rb') as file_r: feature_init_weight_dict[feature_name] = pickle.load(file_r) # 加载数据 # 加载vocs path_vocs = [] for feature_name in feature_names: path_vocs.append(config['data_params']['voc_params'][feature_name]['path']) path_vocs.append(config['data_params']['voc_params']['label']['path']) vocs = load_vocs(path_vocs) # 加载训练数据 sep_str = config['data_params']['sep'] assert sep_str in ['table', 'space'] sep = '\t' if sep_str == 'table' else ' ' data_dict = init_data( path=config['data_params']['path_train'], feature_names=feature_names, sep=sep, vocs=vocs, max_len=config['model_params']['sequence_length'], model='train') # 训练模型 model = SequenceLabelingModel( sequence_length=config['model_params']['sequence_length'], nb_classes=config['model_params']['nb_classes'], nb_hidden=config['model_params']['bilstm_params']['num_units'], feature_weight_shape_dict=feature_weight_shape_dict, feature_init_weight_dict=feature_init_weight_dict, feature_weight_dropout_dict=feature_weight_dropout_dict, dropout_rate=config['model_params']['dropout_rate'], nb_epoch=config['model_params']['nb_epoch'], feature_names=feature_names, batch_size=config['model_params']['batch_size'], train_max_patience=config['model_params']['max_patience'], use_crf=config['model_params']['use_crf'], l2_rate=config['model_params']['l2_rate'], rnn_unit=config['model_params']['rnn_unit'], learning_rate=config['model_params']['learning_rate'], clip=config['model_params']['clip'], path_model=config['model_params']['path_model']) model.fit( data_dict=data_dict, dev_size=config['model_params']['dev_size'])
def predict(testlist): """Prepare the model input data type paramters: testlist: list,[[[u'T'], [u':'],...] return result_sequences: list, """ feature_names, sep, vocs, max_len, use_char_feature, word_len = load_parameters() data_dict = init_data( feature_names=feature_names, sep=sep,test_sens=testlist,vocs=vocs, max_len=max_len, model='test',use_char_feature=use_char_feature,word_len=word_len) # 生成模型feed data data_count = data_dict['f1'].shape[0] nb_test = int(math.ceil(data_count /16.0)) result_sequences = [] # 标记结果 for i in range(nb_test): feed_dict = dict() batch_indices = np.arange(i * 16, (i + 1) * 16) \ if (i+1)*16 <= data_count else \ np.arange(i*16, data_count) batch_data = data_dict['f1'][batch_indices] item = {'input_x_f1': batch_data} feed_dict.update(item) # dropout item = {'weight_dropout_ph_dict_f1': np.array(0.0, dtype=np.float32)} feed_dict.update(item) feed_dict.update({'dropout_rate_ph':np.array(0.,dtype=np.float32), 'rnn_dropout_rate_ph': np.array(0.,dtype=np.float32)}) # viterbi decode procedure logits, sequence_actual_length, transition_params = load_ner_service(feed_dict) for logit, seq_len in zip(logits, sequence_actual_length): logit_actual = logit[:seq_len] viterbi_sequence, _ = tf.contrib.crf.viterbi_decode(logit_actual, transition_params) result_sequences.append(viterbi_sequence) return result_sequences
def pre_feed_data(testlist): # 加载配置文件 feature_names, sep, vocs, max_len, use_char_feature, word_len = load_parameters( ) data_dict = init_data(feature_names=feature_names, sep=sep, test_sens=testlist, vocs=vocs, max_len=max_len, model='test', use_char_feature=use_char_feature, word_len=word_len) # 生成模型feed data data_count = data_dict['f1'].shape[0] nb_test = int(math.ceil(data_count / 16.0)) result_sequences = [] # 标记结果 for i in range(nb_test): feed_dict = dict() batch_indices = np.arange(i * 16, (i + 1) * 16) \ if (i+1)*16 <= data_count else \ np.arange(i*16, data_count) batch_data = data_dict['f1'][batch_indices] item = {'input_x_f1': batch_data} feed_dict.update(item) # dropout item = {'weight_dropout_ph_dict_f1': np.array(0.0, dtype=np.float32)} feed_dict.update(item) feed_dict.update({ 'dropout_rate_ph': np.array(0.0, dtype=np.float32), 'rnn_dropout_rate_ph': np.array(0.0, dtype=np.float32) }) print 'feed_dict_tfserving', feed_dict yield feed_dict
# print('adj2.size = ', adj2.size()) output = model.forward(input1, input2, adj1, adj2) _, pre = torch.max(output, dim=1) tmp = np.zeros((1, 1), dtype=np.int) tmp[0][0] = label tmp_label = torch.from_numpy(tmp) pre = pre.cuda() tmp_label = tmp_label.cuda() if pre[0] == tmp_label[0][0]: acc_num += 1 # print("accuracy : ", acc_num, "of ", test_count) return acc_num * 1.0 / test_count if __name__ == '__main__': my_graphs, max_node_num1, max_node_num2 = init_data(datadir, dataname) random.shuffle(my_graphs) print("数据处理完成", time.asctime(time.localtime(time.time()))) model = GraphClassifier(max_node_num1, max_node_num2) model = model.cuda() print('model:', model) crossentropy = torch.nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(), lr=learning_rate) print('开始训练', time.asctime(time.localtime(time.time()))) max_acc = 0 print_loss = 0 for epoch in range(num_epoches): for i in range(len(my_graphs)): if i > index: break torch.cuda.empty_cache()
def main(): # 加载配置文件 with open('./config.yml') as file_config: config = yaml.load(file_config) feature_names = config['model_params']['feature_names'] use_char_feature = config['model_params']['use_char_feature'] # 初始化embedding shape, dropouts, 预训练的embedding也在这里初始化) feature_weight_shape_dict, feature_weight_dropout_dict, \ feature_init_weight_dict = dict(), dict(), dict() for feature_name in feature_names: feature_weight_shape_dict[feature_name] = \ config['model_params']['embed_params'][feature_name]['shape'] feature_weight_dropout_dict[feature_name] = \ config['model_params']['embed_params'][feature_name]['dropout_rate'] path_pre_train = config['model_params']['embed_params'][feature_name]['path'] if path_pre_train: with open(path_pre_train, 'rb') as file_r: feature_init_weight_dict[feature_name] = pickle.load(file_r) # char embedding shape if use_char_feature: feature_weight_shape_dict['char'] = \ config['model_params']['embed_params']['char']['shape'] conv_filter_len_list = config['model_params']['conv_filter_len_list'] conv_filter_size_list = config['model_params']['conv_filter_size_list'] else: conv_filter_len_list = None conv_filter_size_list = None # 加载数据 # 加载vocs path_vocs = [] if use_char_feature: path_vocs.append(config['data_params']['voc_params']['char']['path']) for feature_name in feature_names: path_vocs.append(config['data_params']['voc_params'][feature_name]['path']) path_vocs.append(config['data_params']['voc_params']['label']['path']) vocs = load_vocs(path_vocs) # 加载数据 sep_str = config['data_params']['sep'] assert sep_str in ['table', 'space'] sep = '\t' if sep_str == 'table' else ' ' max_len = config['model_params']['sequence_length'] word_len = config['model_params']['word_length'] data_dict = init_data( path=config['data_params']['path_test'], feature_names=feature_names, sep=sep, vocs=vocs, max_len=max_len, model='test', use_char_feature=use_char_feature, word_len=word_len) # 加载模型 model = SequenceLabelingModel( sequence_length=config['model_params']['sequence_length'], nb_classes=config['model_params']['nb_classes'], nb_hidden=config['model_params']['bilstm_params']['num_units'], num_layers=config['model_params']['bilstm_params']['num_layers'], feature_weight_shape_dict=feature_weight_shape_dict, feature_init_weight_dict=feature_init_weight_dict, feature_weight_dropout_dict=feature_weight_dropout_dict, dropout_rate=config['model_params']['dropout_rate'], nb_epoch=config['model_params']['nb_epoch'], feature_names=feature_names, batch_size=config['model_params']['batch_size'], train_max_patience=config['model_params']['max_patience'], use_crf=config['model_params']['use_crf'], l2_rate=config['model_params']['l2_rate'], rnn_unit=config['model_params']['rnn_unit'], learning_rate=config['model_params']['learning_rate'], use_char_feature=use_char_feature, conv_filter_size_list=conv_filter_size_list, conv_filter_len_list=conv_filter_len_list, word_length=word_len, path_model=config['model_params']['path_model']) saver = tf.train.Saver() saver.restore(model.sess, config['model_params']['path_model']) # 标记 viterbi_sequences = model.predict(data_dict) # 写入文件 label_voc = dict() for key in vocs[-1]: label_voc[vocs[-1][key]] = key with codecs.open(config['data_params']['path_test'], 'r', encoding='utf-8') as file_r: sentences = file_r.read().strip().split('\n\n') file_result = codecs.open( config['data_params']['path_result'], 'w', encoding='utf-8') for i, sentence in enumerate(sentences): for j, item in enumerate(sentence.split('\n')): if j < len(viterbi_sequences[i]): file_result.write('%s\t%s\n' % (item, label_voc[viterbi_sequences[i][j]])) else: file_result.write('%s\tO\n' % item) file_result.write('\n') file_result.close()
def main(): # 加载配置文件 print("config5") with open('./train_config/config_b2b_tag_5_only_jieba.yml') as file_config: config = yaml.load(file_config) feature_names = config['model_params']['feature_names'] use_char_feature = config['model_params']['use_char_feature'] # 初始化embedding shape, dropouts, 预训练的embedding也在这里初始化) feature_weight_shape_dict, feature_weight_dropout_dict, \ feature_init_weight_dict = dict(), dict(), dict() for feature_name in feature_names: feature_weight_shape_dict[feature_name] = \ config['model_params']['embed_params'][feature_name]['shape'] feature_weight_dropout_dict[feature_name] = \ config['model_params']['embed_params'][feature_name]['dropout_rate'] path_pre_train = config['model_params']['embed_params'][feature_name][ 'path'] if path_pre_train: with open(path_pre_train, 'rb') as file_r: feature_init_weight_dict[feature_name] = pickle.load(file_r) # char embedding shape if use_char_feature: feature_weight_shape_dict['char'] = \ config['model_params']['embed_params']['char']['shape'] conv_filter_len_list = config['model_params']['conv_filter_len_list'] conv_filter_size_list = config['model_params']['conv_filter_size_list'] else: conv_filter_len_list = None conv_filter_size_list = None # 加载数据 # 加载vocs path_vocs = [] if use_char_feature: path_vocs.append(config['data_params']['voc_params']['char']['path']) for feature_name in feature_names: path_vocs.append( config['data_params']['voc_params'][feature_name]['path']) path_vocs.append(config['data_params']['voc_params']['label']['path']) vocs = load_vocs(path_vocs) # 加载训练数据 sep_str = config['data_params']['sep'] assert sep_str in ['table', 'space'] sep = '\t' if sep_str == 'table' else ' ' max_len = config['model_params']['sequence_length'] word_len = config['model_params']['word_length'] data_dict = init_data(path=config['data_params']['path_train'], feature_names=feature_names, sep=sep, vocs=vocs, max_len=max_len, model='train', use_char_feature=use_char_feature, word_len=word_len) # 训练模型 model = SequenceLabelingModel( sequence_length=config['model_params']['sequence_length'], nb_classes=config['model_params']['nb_classes'], nb_hidden=config['model_params']['bilstm_params']['num_units'], num_layers=config['model_params']['bilstm_params']['num_layers'], rnn_dropout=config['model_params']['bilstm_params']['rnn_dropout'], feature_weight_shape_dict=feature_weight_shape_dict, feature_init_weight_dict=feature_init_weight_dict, feature_weight_dropout_dict=feature_weight_dropout_dict, dropout_rate=config['model_params']['dropout_rate'], nb_epoch=config['model_params']['nb_epoch'], feature_names=feature_names, batch_size=config['model_params']['batch_size'], train_max_patience=config['model_params']['max_patience'], use_crf=config['model_params']['use_crf'], l2_rate=config['model_params']['l2_rate'], rnn_unit=config['model_params']['rnn_unit'], learning_rate=config['model_params']['learning_rate'], clip=config['model_params']['clip'], use_char_feature=use_char_feature, conv_filter_size_list=conv_filter_size_list, conv_filter_len_list=conv_filter_len_list, cnn_dropout_rate=config['model_params']['conv_dropout'], word_length=word_len, path_model=config['model_params']['path_model']) model.fit(data_dict=data_dict, dev_size=config['model_params']['dev_size'])
def predict(string): choiceAction = [] choiceTarget = [] choiceData = [] lab = writetxt(string) # 加载数据 if len(lab[0]) == 0: return 'ok;None' sep_str = config['data_params']['sep'] assert sep_str in ['table', 'space'] sep = '\t' if sep_str == 'table' else ' ' data_dict = init_data(path=config['data_params']['path_test'], feature_names=feature_names, sep=sep, vocs=vocs, max_len=config['model_params']['sequence_length'], model='test') saver = tf.train.Saver() saver.restore(model.sess, config['model_params']['path_model']) seq = model.predict(data_dict) print(seq) for i in range(len(seq)): if (vocs[-1]['B_ACT'] in seq[i] or vocs[-1]['I_ACT'] in seq[i] or vocs[-1]['E_ACT'] in seq[i] or vocs[-1]['S_ACT'] in seq[i]): tem = "" for j in range(len(seq[i])): if seq[i][j] == vocs[-1]['B_ACT']: tem = lab[i][j] elif seq[i][j] == vocs[-1]['I_ACT']: tem += lab[i][j] elif seq[i][j] == vocs[-1]['E_ACT']: tem += lab[i][j] choiceAction.append(tem) elif seq[i][j] == vocs[-1]['S_ACT']: choiceAction.append(lab[i][j]) # if len(tem) > 0: # choiceAction.append(tem) ch = '***'.join(choiceAction) finalAction = '' + ch if finalAction == '': finalAction = '0' for i in range(len(seq)): if (vocs[-1]['B_TAR'] in seq[i] or vocs[-1]['I_TAR'] in seq[i] or vocs[-1]['E_TAR'] in seq[i] or vocs[-1]['S_TAR'] in seq[i]): tem = "" for j in range(len(seq[i])): if seq[i][j] == vocs[-1]['B_TAR']: tem = lab[i][j] elif seq[i][j] == vocs[-1]['I_TAR']: tem += lab[i][j] elif seq[i][j] == vocs[-1]['E_TAR']: tem += lab[i][j] choiceTarget.append(tem) elif seq[i][j] == vocs[-1]['S_TAR']: choiceTarget.append(lab[i][j]) # if seq[i][j] == 11: # choiceTarget.append(lab[i][j]) # if len(tem) > 0: # choiceTarget.append(tem) ch = '***'.join(choiceTarget) finalTarget = '' + ch if finalTarget == '': finalTarget = '0' for i in range(len(seq)): if (vocs[-1]['B_DAT'] in seq[i] or vocs[-1]['I_DAT'] in seq[i] or vocs[-1]['E_DAT'] in seq[i] or vocs[-1]['S_DAT'] in seq[i]): tem = "" for j in range(len(seq[i])): if seq[i][j] == vocs[-1]['B_DAT']: tem = lab[i][j] elif seq[i][j] == vocs[-1]['I_DAT']: tem += lab[i][j] elif seq[i][j] == vocs[-1]['E_DAT']: tem += lab[i][j] choiceData.append(tem) elif seq[i][j] == vocs[-1]['S_DAT']: choiceData.append(lab[i][j]) # if len(tem) > 0: # choiceData.append(tem) ch = '***'.join(choiceData) finalData = '' + ch if finalData == '': finalData = '0' return finalAction, finalTarget, finalData
def main(): # 加载配置文件 with open('./config.yml') as file_config: config = yaml.load(file_config) feature_names = config['model_params']['feature_names'] logger.info(feature_names) use_char_feature = config['model_params']['use_char_feature'] logger.info(use_char_feature) # 初始化embedding shape, dropouts, 预训练的embedding也在这里初始化) feature_weight_shape_dict = dict() feature_weight_dropout_dict = dict() feature_init_weight_dict = dict() for feature_name in feature_names: feature_weight_shape_dict[feature_name] = config['model_params'][ 'embed_params'][feature_name]['shape'] feature_weight_dropout_dict[feature_name] = config['model_params'][ 'embed_params'][feature_name]['dropout_rate'] # embeding mat, 比voc多了两行, 因为voc从2开始编序, 0, 1行用0填充 path_pre_train = config['model_params']['embed_params'][feature_name][ 'path'] # 词嵌矩阵位置 # logger.info("%s init mat path: %s" % (feature_name, path_pre_train)) with open(path_pre_train, 'rb') as file_r: feature_init_weight_dict[feature_name] = pickle.load(file_r) logger.info(feature_weight_dropout_dict) logger.info(feature_weight_shape_dict) logger.info(feature_init_weight_dict) # char embedding shape if use_char_feature: # 暂时不考虑 feature_weight_shape_dict['char'] = config['model_params'][ 'embed_params']['char']['shape'] conv_filter_len_list = config['model_params']['conv_filter_len_list'] conv_filter_size_list = config['model_params']['conv_filter_size_list'] else: # 利用卷集层来提取char的信息 conv_filter_len_list = None conv_filter_size_list = None # 加载vocs path_vocs = [] if use_char_feature: path_vocs.append(config['data_params']['voc_params']['char'] ['path']) # vocs用于将文本数字序列化 for feature_name in feature_names: path_vocs.append( config['data_params']['voc_params'][feature_name]['path']) path_vocs.append(config['data_params']['voc_params']['label']['path']) vocs = load_vocs(path_vocs) # 加载训练数据 sep_str = config['data_params']['sep'] assert sep_str in ['table', 'space'] # 数据的分隔方式 sep = '\t' if sep_str == 'table' else ' ' max_len = config['model_params']['sequence_length'] word_len = config['model_params']['word_length'] # 通过voc 将input f1 和输出 label 数字序列化 得到训练的输入和输出 # data_dict = None data_dict = init_data(path=config['data_params']['path_train'], feature_names=feature_names, sep=sep, vocs=vocs, max_len=max_len, model='train', use_char_feature=use_char_feature, word_len=word_len) logger.info(data_dict) # 每个特征序列化后的数据 # 训练模型 model = SequenceLabelingModel( sequence_length=config['model_params']['sequence_length'], # 句子被固定长度 nb_classes=config['model_params']['nb_classes'], nb_hidden=config['model_params']['bilstm_params']['num_units'], num_layers=config['model_params']['bilstm_params']['num_layers'], rnn_dropout=config['model_params']['bilstm_params']['rnn_dropout'], feature_weight_shape_dict=feature_weight_shape_dict, feature_init_weight_dict=feature_init_weight_dict, feature_weight_dropout_dict=feature_weight_dropout_dict, dropout_rate=config['model_params']['dropout_rate'], nb_epoch=config['model_params']['nb_epoch'], feature_names=feature_names, batch_size=config['model_params']['batch_size'], train_max_patience=config['model_params']['max_patience'], use_crf=config['model_params']['use_crf'], l2_rate=config['model_params']['l2_rate'], rnn_unit=config['model_params']['rnn_unit'], learning_rate=config['model_params']['learning_rate'], clip=config['model_params']['clip'], use_char_feature=use_char_feature, conv_filter_size_list=conv_filter_size_list, conv_filter_len_list=conv_filter_len_list, cnn_dropout_rate=config['model_params']['conv_dropout'], word_length=word_len, path_model=config['model_params']['path_model'], last_train_sess_path=None, # 为了加快训练的速度我们继续载入前面训练的参数 transfer=False) # 是否对前面载入的参数进行迁移学习,True的话就重置LSTM的输出层 model.fit(data_dict=data_dict, dev_size=config['model_params']['dev_size']) """
def predict(testlist): # 加载配置文件 with open('./config.yml') as file_config: config = yaml.load(file_config) feature_names = config['model_params']['feature_names'] use_char_feature = config['model_params']['use_char_feature'] # 初始化embedding shape, dropouts, 预训练的embedding也在这里初始化) feature_weight_shape_dict, feature_weight_dropout_dict, \ feature_init_weight_dict = dict(), dict(), dict() for feature_name in feature_names: feature_weight_shape_dict[feature_name] = \ config['model_params']['embed_params'][feature_name]['shape'] feature_weight_dropout_dict[feature_name] = \ config['model_params']['embed_params'][feature_name]['dropout_rate'] path_pre_train = config['model_params']['embed_params'][feature_name][ 'path'] if path_pre_train: with open(path_pre_train, 'rb') as file_r: feature_init_weight_dict[feature_name] = pickle.load(file_r) # char embedding shape if use_char_feature: feature_weight_shape_dict['char'] = \ config['model_params']['embed_params']['char']['shape'] conv_filter_len_list = config['model_params']['conv_filter_len_list'] conv_filter_size_list = config['model_params']['conv_filter_size_list'] else: conv_filter_len_list = None conv_filter_size_list = None # 加载vocs path_vocs = [] if use_char_feature: path_vocs.append(config['data_params']['voc_params']['char']['path']) for feature_name in feature_names: path_vocs.append( config['data_params']['voc_params'][feature_name]['path']) path_vocs.append(config['data_params']['voc_params']['label']['path']) vocs = load_vocs(path_vocs) # 加载数据 sep_str = config['data_params']['sep'] assert sep_str in ['table', 'space'] sep = '\t' if sep_str == 'table' else ' ' max_len = config['model_params']['sequence_length'] word_len = config['model_params']['word_length'] data_dict = init_data(path=config['data_params']['path_test'], feature_names=feature_names, sep=sep, test_sens=testlist, vocs=vocs, max_len=max_len, model='test', use_char_feature=use_char_feature, word_len=word_len) # 加载模型 model = SequenceLabelingModel( sequence_length=config['model_params']['sequence_length'], nb_classes=config['model_params']['nb_classes'], nb_hidden=config['model_params']['bilstm_params']['num_units'], num_layers=config['model_params']['bilstm_params']['num_layers'], feature_weight_shape_dict=feature_weight_shape_dict, feature_init_weight_dict=feature_init_weight_dict, feature_weight_dropout_dict=feature_weight_dropout_dict, dropout_rate=config['model_params']['dropout_rate'], nb_epoch=config['model_params']['nb_epoch'], feature_names=feature_names, batch_size=config['model_params']['batch_size'], train_max_patience=config['model_params']['max_patience'], use_crf=config['model_params']['use_crf'], l2_rate=config['model_params']['l2_rate'], rnn_unit=config['model_params']['rnn_unit'], learning_rate=config['model_params']['learning_rate'], use_char_feature=use_char_feature, conv_filter_size_list=conv_filter_size_list, conv_filter_len_list=conv_filter_len_list, word_length=word_len, path_model=config['model_params']['path_model']) saver = tf.train.Saver() saver.restore(model.sess, config['model_params']['path_model']) # print('data_dict', data_dict) # 标记 result_sequences = model.predict(data_dict) #print('result_sequences', result_sequences) # 输出结果 label_voc = dict() for key in vocs[-1]: label_voc[vocs[-1][key]] = key outlist = [] for i, sentence in enumerate(testlist): templist = [] for j, item in enumerate(sentence): #char = recheck_char(item[0]) char = item[0] if j < len(result_sequences[i]): out = [char, label_voc[result_sequences[i][j]]] else: out = [char, 'O'] templist.append(out) outlist.append(templist) return outlist
# 加载数据 # 加载 vocs path_vocs = [] for feature_name in feature_names: path_vocs.append(config['data_params']['voc_params'][feature_name]['path']) path_vocs.append(config['data_params']['voc_params']['label']['path']) vocs = load_vocs(path_vocs) # 加载训练数据 sep_str = config['data_params']['sep'] assert sep_str in ['table', 'space'] sep = '\t' if sep_str == 'table' else ' ' data_dict = init_data(path=config['data_params']['path_train'], feature_names=feature_names, sep=sep, vocs=vocs, max_len=config['model_params']['sequence_length'], model='train') # 训练模型 model = SequenceLabelingModel( sequence_length=config['model_params']['sequence_length'], nb_classes=config['model_params']['nb_classes'], nb_hidden=config['model_params']['bilstm_params']['num_units'], feature_weight_shape_dict=feature_weight_shape_dict, feature_init_weight_dict=feature_init_weight_dict, feature_weight_dropout_dict=feature_weight_dropout_dict, dropout_rate=config['model_params']['dropout_rate'], nb_epoch=config['model_params']['nb_epoch'], feature_names=feature_names, batch_size=config['model_params']['batch_size'],