我想从输入文本中预测8个类别。以下是我预处理数据的代码：
num_max = 1000tok = Tokenizer(num_words=num_max)tok.fit_on_texts(x_train)mat_texts = tok.texts_to_matrix(x_train,mode='count')num_max = 1000tok = Tokenizer(num_words=num_max)tok.fit_on_texts(x_train)max_len = 100cnn_texts_seq = tok.texts_to_sequences(x_train)print(cnn_texts_seq[0])[12, 4, 303]# 填充序列cnn_texts_mat = sequence.pad_sequences(cnn_texts_seq,maxlen=max_len)print(cnn_texts_mat[0])print(cnn_texts_mat.shape)[ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 12 4 303](301390, 100)以下是包含嵌入层的模型结构：
max_features = 20000max_features = cnn_texts_mat.shape[1]maxlen = 100embedding_size = 128model = Sequential()model.add(Embedding(max_features, embedding_size, input_length=maxlen))model.add(Dropout(0.2))model.add(Dense(5000, activation='relu'))model.add(Dropout(0.1))model.add(Dense(600, activation='relu'))model.add(Dropout(0.1))model.add(Dense(units=y_train.shape[1], activation='softmax'))sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)model.compile(loss='binary_crossentropy', optimizer=sgd)以下是模型摘要：
model.summary()_________________________________________________________________Layer (type) Output Shape Param # =================================================================embedding_5 (Embedding) (None, 100, 128) 12800 _________________________________________________________________dropout_13 (Dropout) (None, 100, 128) 0 _________________________________________________________________dense_13 (Dense) (None, 100, 5000) 645000 _________________________________________________________________dropout_14 (Dropout) (None, 100, 5000) 0 _________________________________________________________________dense_14 (Dense) (None, 100, 600) 3000600 _________________________________________________________________dropout_15 (Dropout) (None, 100, 600) 0 _________________________________________________________________dense_15 (Dense) (None, 100, 8) 4808 =================================================================Total params: 3,663,208Trainable params: 3,663,208Non-trainable params: 0在此之后，当我尝试运行模型时，出现了以下错误：
model.fit(x=cnn_texts_mat, y=y_train, epochs=2, batch_size=100)ValueError Traceback (most recent call last)<ipython-input-41-4b9da9914e7e> in <module>----> 1 model.fit(x=cnn_texts_mat, y=y_train, epochs=2, batch_size=100)~/.local/lib/python3.5/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs) 950 sample_weight=sample_weight, 951 class_weight=class_weight,--> 952 batch_size=batch_size) 953 # Prepare validation data. 954 do_validation = False~/.local/lib/python3.5/site-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size) 787 feed_output_shapes, 788 check_batch_axis=False, # Don't enforce the batch size.--> 789 exception_prefix='target') 790 791 # Generate sample-wise weight values given the `sample_weight` and~/.local/lib/python3.5/site-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix) 126 ': expected ' + names[i] + ' to have ' + 127 str(len(shape)) + ' dimensions, but got array '--> 128 'with shape ' + str(data_shape)) 129 if not check_batch_axis: 130 data_shape = data_shape[1:]ValueError: 检查目标时出错：期望dense_15具有3个维度，但得到的数组形状为(301390, 8)回答：
查看模型摘要中最后一层的输出形状：它是(None, 100, 8)。这并不是你想要的。每个样本的标签形状为(8,)，而不是(100,8)。为什么会这样？这是因为Dense层应用于其输入的最后一个轴，因此由于嵌入层的输出是3D的，所有后续的Dense层的输出也将具有3个维度。
如何解决这个问题？一种方法是在模型的某个地方使用Flatten层（可能是在嵌入层之后）。这样你将得到一个形状为(None, 8)的2D输出，这是你想要的，并且与标签的形状一致。
但是，请注意，你可能会得到一个非常大的模型（即参数过多），这将很容易过拟合。要么减少Dense层中的单元数，要么选择使用Conv1D和MaxPooling1D层，甚至是RNN层来处理嵌入并降低结果张量的维度（使用这些层也可能提高模型的准确性）。
