无法在“ float”和“ list”的实例之间使用validation_data“ <”来训练暹罗语

问题描述

当我使用keras model.fit而不使用“ validation_data”并且仅使用x_train和y_train时，即使使用“ validation_split”，我也不会出现任何错误，但一切正常。下面是工作代码

def siamese(x_train,y_train):

    W_init = tf.keras.initializers.he_normal(seed=100)
    b_init = tf.keras.initializers.he_normal(seed=50)

    input_shape = (24,939)
    left_input = Input(input_shape)
    right_input = Input(input_shape)

    encoder = Sequential()
    encoder.add(Conv1D(filters=6,kernel_size=4,padding='same',activation='relu',input_shape=input_shape,kernel_initializer=W_init,bias_initializer=b_init))
    encoder.add(BatchNormalization())
    encoder.add(Dropout(.1))
    encoder.add(MaxPool1D())
    encoder.add(Conv1D(filters=4,kernel_size=3,activation='relu'))
    encoder.add(BatchNormalization())
    encoder.add(Dropout(.1))
    encoder.add(MaxPool1D())
    encoder.add(Conv1D(filters=3,kernel_size=2,activation='relu'))
    encoder.add(BatchNormalization())
    encoder.add(Dropout(.1))
    encoder.add(MaxPool1D())
    encoder.add(Flatten())
    encoder.add(Dense(64,activation='relu'))
    encoder.add(Dropout(.3))

    encoded_l = encoder(left_input)
    encoded_r = encoder(right_input)
    distance = Lambda(euclidean_distance,output_shape=eucl_dist_output_shape)([encoded_l,encoded_r])
    adam = optimizers.Adam(lr=.001)
    earlyStopping = EarlyStopping(monitor='loss',min_delta=0,patience=3,verbose=1,restore_best_weights=False)
    callback_early_stop_reduceLROnPlateau=[earlyStopping]
    model = Model([left_input,right_input],distance)
    model.compile(loss=contrastive_loss,optimizer=adam,metrics=[accuracy])
    model.summary()
    history = model.fit([(x_train[:,:,0]).astype(np.float32),(x_train[:,1]).astype(np.float32)],y_train,validation_split = .15,batch_size=64,epochs=4,callbacks=callback_early_stop_reduceLROnPlateau)
    return model,history

model1,history1=siamese(xtrain_np_img1_img2,y_train_numpy)

输出::::

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_5 (InputLayer)            (None,24,939)      0                                            
__________________________________________________________________________________________________
input_6 (InputLayer)            (None,939)      0                                            
__________________________________________________________________________________________________
sequential_3 (Sequential)       (None,64)           23337       input_5[0][0]                    
                                                                 input_6[0][0]                    
__________________________________________________________________________________________________
lambda_3 (Lambda)               (None,1)            0           sequential_3[1][0]               
                                                                 sequential_3[2][0]               
==================================================================================================
Total params: 23,337
Trainable params: 23,311
Non-trainable params: 26
__________________________________________________________________________________________________
Train on 12653 samples,validate on 2233 samples
Epoch 1/4
12653/12653 [==============================] - 8s 668us/step - loss: 5.2016 - accuracy: 0.4152 - val_loss: 0.1739 - val_accuracy: 0.7323
Epoch 2/4
12653/12653 [==============================] - 7s 533us/step - loss: nan - accuracy: 0.4359 - val_loss: nan - val_accuracy: 1.0000
Epoch 3/4
12653/12653 [==============================] - 7s 539us/step - loss: nan - accuracy: 0.4117 - val_loss: nan - val_accuracy: 1.0000
Epoch 4/4
12653/12653 [==============================] - 7s 532us/step - loss: nan - accuracy: 0.4117 - val_loss: nan - val_accuracy: 1.0000
Epoch 00004: early stopping

现在我想介绍“ validation_data”，而不要使用“ validation_split”

所以我先尝试了

def siamese(x_train,x_val,y_val):

    W_init = tf.keras.initializers.he_normal(seed=100)
    b_init = tf.keras.initializers.he_normal(seed=50)

    input_shape = (24,tuple([(x_val[:,(x_val[:,1]).astype(np.float32)]),y_val,batch_size=128,y_train_numpy,xtest_np_img1_img2,y_test_numpy)

我得到的错误是 TypeError：fit（）为参数'batch_size'获取了多个值

所以我尝试了另一种方法，因为我无法解决以上问题

def siamese(x_train,batch_size,epochs,callbacks):

    W_init = tf.keras.initializers.he_normal(seed=100)
    b_init = tf.keras.initializers.he_normal(seed=50)

    input_shape = (24,callbacks)
    return model,y_test_numpy,64,4,callback_early_stop_reduceLROnPlateau)

现在这次错误是

TypeError                                 Traceback (most recent call last)
<ipython-input-17-fd746aea477d> in <module>
----> 1 model1,callback_early_stop_reduceLROnPlateau)

<ipython-input-15-cebaa8a123ad> in siamese(x_train,callbacks)
     36     model.summary()
---> 38     history = model.fit([(x_train[:,callbacks)
     39     return model,history

~\AppData\Roaming\Python\Python37\site-packages\keras\engine\training.py in fit(self,x,y,verbose,callbacks,validation_split,validation_data,shuffle,class_weight,sample_weight,initial_epoch,steps_per_epoch,validation_steps,validation_freq,max_queue_size,workers,use_multiprocessing,**kwargs)
   1179                 val_inputs = val_x + val_y + val_sample_weights
   1180 
-> 1181         elif validation_split and 0. < validation_split < 1.:
   1182             if any(K.is_tensor(t) for t in x):
   1183                 raise ValueError(

TypeError: '<' not supported between instances of 'float' and 'list'

我很确定我在学习机器学习时犯了一些小错误。

我之所以尝试这样做，是因为我想使用一个名为“ talos”的工具，并且因为我正在与暹罗网络合作，该网络需要多个输入，并且talos才能正常工作，所以我不能使用validation_split，但可以使用validation_data https://autonomio.github.io/talos/#/Examples_Multiple_Inputs

我之所以要使用talos的原因是为了查询另一个线程，因为我的模型表现不佳，所以我想可能是我应该首先尝试超参数调整。

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）