情绪分析:拟合模型会导致数值误差(形状不兼容?)

Question

我正在对一组评论进行情绪分析->基于所述文本评论来预测所述评级(0-5(。我已经完成了文本预处理和标记化。我使用了一个预先训练好的单词向量嵌入(googlenews(，并创建了embedding_matrix。

到目前为止，我已经建立了模型：

#defining X (padded) and y and completing train/test split
X = pad_sequences(sequences, maxlen= 1000)
y = df['rating']
X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = 0.25, random_state = 1000)
y_train = to_categorical(y_train,6)
#building the model
sentiment_wv_model = Sequential()
embed_layer = Embedding(vocab_size, 100,weights = [embedding_matrix], input_length = 1000,trainable = True)
sentiment_wv_model.add(embed_layer)
sentiment_wv_model.add(Dense(100, activation = 'sigmoid'))
sentiment_wv_model.add(Dense(32, activation = 'sigmoid'))
sentiment_wv_model.add(Dense(1, activation='softmax'))

#compile model and fit to train data
sentiment_wv_model.compile(loss = 'categorical_crossentropy',optimizer = 'adam', metrics =['accuracy'])
sentiment_wv_model.summary
_________________________________________________________________
Layer (type)                Output Shape              Param #   
=================================================================
embedding_1 (Embedding)     (None, 1000, 100)         3631400   

dense (Dense)               (None, 1000, 100)         10100     

dense_1 (Dense)             (None, 1000, 32)          3232      

dense_2 (Dense)             (None, 1000, 2)           66        

dense_3 (Dense)             (None, 1000, 1)           3         

dense_4 (Dense)             (None, 1000, 100)         200       

dense_5 (Dense)             (None, 1000, 32)          3232      

dense_6 (Dense)             (None, 1000, 1)           33        

=================================================================
Total params: 3,648,266
Trainable params: 3,648,266
Non-trainable params: 0
_________________________________________________________________

sentiment_wv_model.fit(X_train, y_train, batch_size = 32, epochs = 5, verbose =2)

运行这个，我得到以下错误：

ValueError: in user code:
File "C:UserstammyAnaconda3libsite-packageskerasenginetraining.py", line 878, in train_function  *
return step_function(self, iterator)
File "C:UserstammyAnaconda3libsite-packageskerasenginetraining.py", line 867, in step_function  **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:UserstammyAnaconda3libsite-packageskerasenginetraining.py", line 860, in run_step  **
outputs = model.train_step(data)
File "C:UserstammyAnaconda3libsite-packageskerasenginetraining.py", line 809, in train_step
loss = self.compiled_loss(
File "C:UserstammyAnaconda3libsite-packageskerasenginecompile_utils.py", line 201, in __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File "C:UserstammyAnaconda3libsite-packageskeraslosses.py", line 141, in __call__
losses = call_fn(y_true, y_pred)
File "C:UserstammyAnaconda3libsite-packageskeraslosses.py", line 245, in call  **
return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "C:UserstammyAnaconda3libsite-packageskeraslosses.py", line 1664, in categorical_crossentropy
return backend.categorical_crossentropy(
File "C:UserstammyAnaconda3libsite-packageskerasbackend.py", line 4994, in categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
ValueError: Shapes (None, 6, 6) and (None, 1000, 1) are incompatible

我看到这种类型的问题已经被问过几次了，但我尝试过其他解决方案，比如将y设置为"to_categorical"，更改激活函数或切换为"binary_crossentropy"(后两个对我来说没有意义，但我还是试过了(。请告知！

Answer 1

您当前的y值有一个稀疏张量：

y_train = to_categorical(y_train,6)

这个应该有[1000,6]的形状，你可以用y_train.shape()来检查。

应该起作用的一件事是简单地将输出层的大小更改为6:

sentiment_wv_model.add(Dense(6, activation='softmax'))

[可选]之后，您还可以将您的损失更改为稀疏_类别_交叉熵：

sentiment_wv_model.compile(loss = tf.keras.losses.SparseCategoricalCrossentropy,optimizer = 'adam', metrics =['accuracy'])

此外，您应该考虑在Embedding层之后使数据变平，以便获得输出形状(None, 6)而不是(None, 1000, 6)