ValueError:`class_weight`必须包含数据中的所有类。类{1,2,3}存在于数据中,但不存在于`class_weight`中

时间:2018-02-28 14:00:04

标签: python numpy tensorflow deep-learning keras

  

ValueError:class_weight必须包含数据中的所有类。类{1,2,3}存在于数据中,但不存在于class_weight

我正在尝试将类权重分配给我的非平衡类,但是在model.fit()之后,它会生成此错误,尽管我已经看到已经为此问题提供了其他解决方案但仍然无法解决它。

test_split=round(n*2/3)
x_train=x[:test_split]
y_train=y[:test_split]
x_test=x[test_split:]
y_test=y[test_split:]

class_weight_list = compute_class_weight('balanced', numpy.unique(y_train), y_train)
class_weight = dict(zip(numpy.unique(y_train), class_weight_list))
x_train=x_train.astype('float64')
x_test=x_test.astype('float64')

x_train/=255
x_test/=255

y_train=keras.utils.to_categorical(y_train, num_classes)
y_test=keras.utils.to_categorical(y_test, num_classes)
hist=model.fit(x_train, y_train, 
               batch_size=batch_size,
               epochs=epochs,
               validation_data=(x_test, y_test),
               callbacks=[checkpoint],
               class_weight=class_weight
               )

1 个答案:

答案 0 :(得分:0)

首先尝试标签编码

修改

encoder = LabelEncoder()
encoder.fit(y_train)
y_train= encoder.transform(y_train)
y_test= encoder.transform(y_test)

class_weight_list = compute_class_weight('balanced', numpy.unique(y_train), y_train)
class_weight = dict(zip(numpy.unique(y_train), class_weight_list))

y_train=keras.utils.to_categorical(y_train, num_classes)