python - Raising ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray)

Question

I have below keras code :

from numpy import loadtxt
from keras.models import Sequential
from keras.layers import Dense
model = Sequential()
model.add(Dense(12, input_dim=5, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(x, y, epochs=10, batch_size=1)

That raises ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray).

My x dataset and types is shown below. x dtype is object and each element of that has int64. So How to convert x dtype:object to array to pass in keras model.

Answer 1

等待大神答复