(Keras)ValueError:无法将NumPy数组转换为张量(不受支持的对象类型float) [英] (Keras) ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float)

问题描述

我知道此问题已在下面的链接中得到了解答，但不适用于我的情况.(

I know this problem has been answered previously in the link below,but it does not apply to my situation.(Tensorflow - ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float))

我的预测变量(X)和目标变量(y)均为<class 'numpy.ndarray'>，它们的形状分别为 X:(8981，25) y:(8981，1)

Both my predictor (X) and target variables (y) are <class 'numpy.ndarray'> and their shapes are X: (8981, 25) y: (8981, 1)

但是，我仍然收到错误消息. ValueError:无法将NumPy数组转换为张量(不受支持的对象类型float).

Yet, I am still getting the error message. ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float).

请参考以下代码:

import tensorflow as tf
ndim = X.shape[1]
model = tf.keras.models.Sequential()
# model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(36, activation = tf.nn.relu, input_dim=ndim))
model.add(tf.keras.layers.Dense(36, activation = tf.nn.relu))
model.add(tf.keras.layers.Dense(2, activation = tf.nn.softmax))
model.compile(optimizer = 'adam',
              loss = 'sparse_categorical_crossentropy',
              metrics = ['accuracy'])
model.fit(X.values, y, epochs = 5)
y_pred = model.predict([X_2019])

任何帮助将不胜感激！谢谢!!!

Any help will be really appreciated! Thanks!!!

推荐答案

在创建np数组时尝试插入dtype=np.float:

Try inserting dtype=np.float when creating the np array:

np.array(*your list*, dtype=np.float)

这篇关于(Keras)ValueError:无法将NumPy数组转换为张量(不受支持的对象类型float)的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！