Question

这是印地语OCR的代码，图像具有1024个尺寸，程序尝试将其分为46类。到目前为止，我正在将Keras与Tensorflow后端一起使用，而没有任何隐藏层。这是代码：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import LabelEncoder



dataset = pd.read_csv('data.csv')
print(dataset.head())
x = dataset.iloc[:,:-1]
y = dataset.iloc[:,-1]

print(y[0:5])
label_encoder = LabelEncoder()
y = label_encoder.fit_transform(y.values)
y = y.T
print(x.shape)
x_train,x_test,y_train,y_test = train_test_split(x.values,y)
print(y.shape)
print(np.unique(y))

from keras import Sequential
from keras.layers import Dense, Dropout
model = Sequential()
model.add(Dense(1024, activation='relu', input_dim=1024))
model.add(Dense(46, activation='softmax'))
model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

model.fit(x_train, y_train,
          epochs=20,
          batch_size=128)
score = model.evaluate(x_test, y_test)

这是错误回溯：

--------------------------------------------------------------------------- ValueError                                Traceback (most recent call last) <ipython-input-10-52e9b7f77a5d> in <module>()
      2 model.fit(x_train, y_train,
      3           epochs=20,
----> 4           batch_size=128)
      5 score = model.evaluate(x_test, y_test)

~\Anaconda3\lib\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)
    948             sample_weight=sample_weight,
    949             class_weight=class_weight,
--> 950             batch_size=batch_size)
    951         # Prepare validation data.
    952         do_validation = False

~\Anaconda3\lib\site-packages\keras\engine\training.py in
_standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
    785                 feed_output_shapes,
    786                 check_batch_axis=False,  # Don't enforce the batch size.
--> 787                 exception_prefix='target')
    788 
    789             # Generate sample-wise weight values given the `sample_weight` and

~\Anaconda3\lib\site-packages\keras\engine\training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    135                             ': expected ' + names[i] + ' to have shape ' +
    136                             str(shape) + ' but got array with shape ' +
--> 137                             str(data_shape))
    138     return data
    139 

ValueError: Error when checking target: expected dense_6 to have shape (46,) but got array with shape (1,)

Answer 1

您需要使用keras.utils.to_categorical()对标签（即y）进行一次热编码，或者可以使用'sparse_categorical_crossentropy'作为损失函数来使其与稀疏标签一起使用。

ValueError：检查目标时出错：预期density_6的形状为（46，），但数组的形状为（1，）

1 个答案: