TensorFlow ValueError：无法将NumPy数组转换为Tensor不支持的对象类型列表

问题描述

我正在尝试将this code写入colab。有趣的是，几天前我在colab中运行了相同的代码，但现在无法正常工作。该代码也可以在kaggle内核中使用。我尝试更改TensorFlow版本，但它们都给出了不同的错误。为什么您认为我无法运行此代码？如果您需要更多信息，则为colab notebook。 预先感谢！

DisasterDetector类：

def __init__(self,tokenizer,bert_layer,max_len =30,lr = 0.0001,epochs = 15,batch_size = 32,dtype = tf.int32,activation = 'sigmoid',optimizer = 'SGD',beta_1=0.9,beta_2=0.999,epsilon=1e-07,metrics = 'accuracy',loss = 'binary_crossentropy'):
    
    self.lr = lr
    self.epochs = epochs
    self.max_len = max_len
    self.batch_size = batch_size
    self.tokenizer = tokenizer
    self.bert_layer = bert_layer
    self.models = []

    self.activation = activation
    self.optimizer = optimizer
    self.dtype = dtype
    
    self.beta_1 = beta_1
    self.beta_2 = beta_2
    self.epsilon =epsilon
    
    self.metrics = metrics
    self.loss = loss
    
def encode(self,texts):
    all_tokens = []
    masks = []
    segments = []
    
    for text in texts:
        
        tokenized = self.tokenizer.convert_tokens_to_ids(['[CLS]'] + self.tokenizer.tokenize(text) + ['[SEP]'])
        
        len_zeros = self.max_len - len(tokenized)
        
        
        padded = tokenized + [0] * len_zeros
        mask = [1] * len(tokenized) + [0] * len_zeros
        segment = [0] * self.max_len
        
        all_tokens.append(padded)
        masks.append(mask)
        segments.append(segment)
        
    print(len(all_tokens[0]))
    return np.array(all_tokens),np.array(masks),np.array(segments)
    
def make_model(self):
    

    input_word_ids = Input(shape = (self.max_len,),dtype=tf.int32,name = 'input_word_ids')
    
    input_mask = Input(shape = (self.max_len,name = 'input_mask')
    
    segment_ids = Input(shape = (self.max_len,name = 'segment_ids')


    #pooled output is the output of dimention and

    pooled_output,sequence_output = self.bert_layer([input_word_ids,input_mask,segment_ids])

    clf_output = sequence_output[:,:]
    out = tf.keras.layers.Dense(1,activation = self.activation)(clf_output)
    #out = tf.keras.layers.Dense(1,input_shape =  (clf_output,) )(clf_output)
    

    model = Model(inputs = [input_word_ids,segment_ids],outputs = out)
    if self.optimizer is 'SGD':
        optimizer = SGD(learning_rate = self.lr)

    elif self.optimizer is 'Adam': 
        optimizer = Adam(learning_rate = self.lr,beta_1=self.beta_1,beta_2=self.beta_2,epsilon=self.epsilon)

    model.compile(loss = self.loss,optimizer = self.optimizer,metrics = [self.metrics])
    
    return model




def train(self,x,k = 3):    
    kfold = StratifiedKFold(n_splits = k,shuffle = True)


    for fold,(train_idx,val_idx) in enumerate(kfold.split(x['cleaned_text'],x['target'])):
        print('fold: ',fold)

        x_trn = self.encode(x.loc[train_idx,'cleaned_text'])
        x_val = self.encode(x.loc[val_idx,'cleaned_text'])
        y_trn = np.array(x.loc[train_idx,'target'],dtype = np.uint8)
        y_val = np.array(x.loc[val_idx,dtype = np.uint8)
        print('the data type of y train: ',type(y_trn))
        print('x_val shape',x_val[0].shape)
        print('x_trn shape',x_trn[0].shape)
        
        model = self.make_model()
        print('model made.')
        model.fit(x_trn,tf.convert_to_tensor(y_trn),validation_data = (x_val,tf.convert_to_tensor(y_val)),batch_size=self.batch_size,epochs = self.epochs)

        self.models.append(model)

并且在调用该类的训练函数后，我得到了该错误。

classifier = DisasterDetector(tokenizer = tokenizer,bert_layer = bert_layer,max_len = max_len,epochs = 10,epsilon=1e-07)
classifier.train(train_cleaned)

这是错误：

ValueError                                Traceback (most 

recent call last)
<ipython-input-10-106c756f2e47> in <module>()
----> 1 classifier.train(train_cleaned)

8 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py in convert_to_eager_tensor(value,ctx,dtype)
     96       dtype = dtypes.as_dtype(dtype).as_datatype_enum
     97   ctx.ensure_initialized()
---> 98   return ops.EagerTensor(value,ctx.device_name,dtype)
     99 
    100 

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type list).

解决方法

好吧，事实证明，由于没有给出适当的最大序列长度，TensorFlow会引发此错误。通过将max_len变量更改为54，我可以毫无困难地运行程序。因此，问题不在于输入的类型或numpy数组。