Question

我正在尝试使用Keras和python训练一个简单的模型。文本经过了完美的预处理。但是当我尝试适应它时，出现以下错误：

df <- data.frame(x = 1:10, y = 1:10)
library(ggplot2)
ggplot(df, aes(x, y)) + 
    geom_point() +
    # Y position adjusted manually
    geom_text(aes(5, 2.9, label = "-"), color = "blue", size = 1000)  +
    # Y position adjusted manually
    geom_text(aes(5, 21.2, label = "-"), color = "blue", size = 1000)  +
    # Plot outside plot area
    coord_cartesian(ylim = c(0, 10), clip = "off")

但是File "main.py", line 47, in <module> model.fit(x_train, y_train, batch_size=32, epochs=3) File "/home/shamildacoder/.local/lib/python3.6/site-packages/keras/engine/training.py", line 952, in fit batch_size=batch_size) File "/home/shamildacoder/.local/lib/python3.6/site-packages/keras/engine/training.py", line 789, in _standardize_user_data exception_prefix='target') File "/home/shamildacoder/.local/lib/python3.6/site-packages/keras/engine/training_utils.py", line 138, in standardize_input_data str(data_shape)) ValueError: Error when checking target: expected dense_2 to have shape (121885,) but got array with shape (1000,)和print(x_train.shape)都返回print(y_train.shape)。我没看到任何原因。

代码：https://pastebin.com/afnzBf6B

(121885, 1000)

Answer 1

在预处理阶段，您使用texts_to_matrix()方法（具有默认参数）将给定序列作为单行编码格式的矩阵行返回。现在，如果您只想使用密集层将一个热编码序列转换为另一个热编码序列，则需要将最后一层中的单位数设置为词汇表大小（即，矩阵），并使用@unique作为最后一层的激活函数：

sigmoid

Keras关于数组形状的错误，但形状似乎正确

1 个答案: