Keras: 'Sequential' object has no attribute '_feed_input_names'

Question

I try to create a multi-label classificator using Keras. The training data has the following format:

X_train

y_train:

This is the code that I use to build the model:

from keras.models import Sequential
from keras.layers import Dense
import math

def softmax(z):
    z_exp = [math.exp(i) for i in z]
    sum_z_exp = sum(z_exp)
    return [i / sum_z_exp for i in z_exp]

nn = Sequential()
nn.add(Dense(10, activation="relu", input_shape=(10,)))
nn.add(Dense(2, activation="sigmoid"))

nn.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

n = 10000
model.fit(X_train.values, y_train.values, batch_size=16, epochs=5, verbose=1, validation_split=0.1)

When I run this code, it fails with the message:

AttributeError: 'Sequential' object has no attribute '_feed_input_names'

A few hints, use activation='softmax' instead of using your custom softmax. That's because you are not using Keras symbolic tensors in that function. But since this code doesn't seem to use this activation, the problem is likely to be in X_train.values and Y_train.values. Make sure they both are numpy arrays with print(type(X_train.values)). — Daniel Möller
– Daniel Möller, Commented Sep 19, 2019 at 13:59

Fabian · Accepted Answer · 2019-09-19 14:04:25Z

1

I' m writing my suggestions here because i can't comment yet. I think your input_shape might be off. You can find here and here that someone other had the same problem. Maybe try something like:

nn.add(Dense(.... input_dim=X_train.shape[1]))

I hope this helps :)

answered Sep 19, 2019 at 14:04

Fabian

8026 silver badges12 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Keras: 'Sequential' object has no attribute '_feed_input_names'

1 Answer 1

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related