Skip to main content
 首页 » 编程设计

python之保存和恢复 Keras BLSTM CTC 模型

2025年01月19日10powertoolsteam

我一直在研究语音情感识别深度神经网络。我使用了带有 CTC 损失的 keras 双向 LSTM。我训练了模型并保存了

model_json = model.to_json() 打开(“ctc_model.json”,“w”)作为 json_file: json_file.write(model_json) 模型.save_weights("ctc_weights.h5")

问题是我不能使用这个模型来测试看不见的数据,因为模型接受 4 个参数作为输入并计算 ctc 损失..只需构建模型和训练。那么我怎样才能以只需要一个输入的方式保存模型。不是标签和长度。基本上我如何将模型保存为这个函数 test_func = K.function([net_input], [output])

def ctc_lambda_func(args): 
    y_pred, labels, input_length, label_length = args 
 
   shift = 2 
   y_pred = y_pred[:, shift:, :] 
   input_length -= shift 
   return K.ctc_batch_cost(labels, y_pred, input_length, label_length) 
def build_model(nb_feat, nb_class, optimizer='Adadelta'): 
    net_input = Input(name="the_input", shape=(200, nb_feat)) 
    forward_lstm1  = LSTM(output_dim=64,  
                      return_sequences=True,  
                      activation="tanh" 
                     )(net_input) 
    backward_lstm1 = LSTM(output_dim=64,  
                      return_sequences=True,  
                      activation="tanh", 
                      go_backwards=True 
                     )(net_input) 
    blstm_output1  = Merge(mode='concat')([forward_lstm1, backward_lstm1]) 
 
    forward_lstm2  = LSTM(output_dim=64,  
                      return_sequences=True,  
                      activation="tanh" 
                     )(blstm_output1) 
    backward_lstm2 = LSTM(output_dim=64,  
                      return_sequences=True,  
                      activation="tanh", 
                      go_backwards=True 
                     )(blstm_output1) 
    blstm_output2  = Merge(mode='concat')([forward_lstm2, backward_lstm2]) 
 
    hidden = TimeDistributed(Dense(512, activation='tanh'))(blstm_output2) 
    output = TimeDistributed(Dense(nb_class + 1, activation='softmax')) (hidden) 
 
    labels = Input(name='the_labels', shape=[1], dtype='float32') 
    input_length = Input(name='input_length', shape=[1], dtype='int64') 
    label_length = Input(name='label_length', shape=[1], dtype='int64') 
    loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name="ctc")([output, labels, input_length, label_length]) 
    model = Model(input=[net_input, labels, input_length, label_length], output=[loss_out]) 
    model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=optimizer, metrics=[]) 
 
    test_func = K.function([net_input], [output]) 
 
    return model, test_func 
model, test_func = build_model(nb_feat=nb_feat, nb_class=nb_class, optimizer=optimizer) 
 for epoch in range(number_epoches): 
     inputs_train = {'the_input': X_train[i:i+batch_size], 
                    'the_labels': y_train[i:i+batch_size], 
                    'input_length': np.sum(X_train_mask[i:i+batch_size], axis=1, dtype=np.int32), 
                    'label_length': np.squeeze(y_train_mask[i:i+batch_size]), 
                   } 
     outputs_train = {'ctc': np.zeros([inputs_train["the_labels"].shape[0]])} 
 
    ctcloss = model.train_on_batch(x=inputs_train, y=outputs_train) 
 
    total_ctcloss += ctcloss * inputs_train["the_input"].shape[0] * 1. 
loss_train[epoch] = total_ctcloss / X_train.shape[0] 

Here is the my model summary 

请您参考如下方法:

尝试以下解决方案:

import keras.backend as K 
 
def get_prediction_function(model): 
    input_tensor = model.layers[0].input 
    output_tensor = model.layers[-5].output 
    net_function = K.function([input_tensor, K.learning_phase()], [output_tensor]) 
    def _result_function(x): 
        return net_function([x, 0])[0] 
    return _result_function 

现在您的网络功能可能通过以下方式获得:

test_function = get_prediction_function(model)