Question

我对keras尚不熟悉，因此我正在与keras一起进行情绪分析项目，但我没有解决此问题的任何观点：这是我的keras模型

       model = Sequential()

      model.add(Conv1D(32, kernel_size=3, activation='elu', padding='same', 
      input_shape=(15, 512)))
      model.add(Conv1D(32, kernel_size=3, activation='elu', padding='same'))
      model.add(Conv1D(32, kernel_size=3, activation='elu', padding='same'))
      model.add(Conv1D(32, kernel_size=3, activation='elu', padding='same'))
      model.add(Dropout(0.25))
      model.add(Conv1D(32, kernel_size=2, activation='elu', padding='same'))
      model.add(Conv1D(32, kernel_size=2, activation='elu', padding='same'))
      model.add(Conv1D(32, kernel_size=2, activation='elu', padding='same'))
      model.add(Conv1D(32, kernel_size=2, activation='elu', padding='same'))
      model.add(Dropout(0.25))
      model.add(Flatten())
      model.add(Dense(256, activation='tanh'))
      model.add(Dense(256, activation='tanh'))
     model.add(Dropout(0.5))
     model.add(Dense(2, activation='softmax'))

   ......preprocessing for new input.....

  pred = model.predict(np.array(final))
  print("%s sentiment; %f%% confidence" % (labels[np.argmax(pred)], pred[0] 
  [np.argmax(pred)] * 100))

****假定final作为输入当我想预测输入的情绪时，我会遇到此错误：

ValueError: Error when checking model input: the list of Numpy arrays that 
you are passing to your model is not the size the model expected. Expected to 
see 1 array(s), but instead got the following list of 3 arrays: [array([[ 
0.08031651,  0.05684812,  0.22872323, ..., -0.19047852

抱歉，这是一个愚蠢的问题！我知道在SOF中有人问过它几次，但是我做了他们的大部分建议，由于我对kras的了解不多，看来这对我来说不切实际

非常感谢

Answer 1

删除您的代码，将该代码添加到该链接中存在的代码之后

from nltk import word_tokenize
import numpy as np


vector_size=512
padding=np.zeros((vector_size ))
sentences=['im so happy','you are beautiful','i got scolded today']

final=[]
for sentence in sentences:
    temp=[]
    words=word_tokenize(sentence)
    for word in words:
        if word in X_vecs:
            temp.append(X_vecs[words])

    #padding to get length of 15
    for i in range(15-len(temp)):
        temp.append(padding)
    final.append(temp)



predictions = model.predict(np.array(final))

for prediction in predictions:
    print("%s sentiment; %f%% confidence" % (labels[np.argmax(prediction)], prediction[np.argmax(prediction)] * 100))

您能运行一下并报告我吗？如果可行，我将解释代码。

预计将看到1个数组，但获得了以下3个数组的列表

1 个答案: