ValueError: Layer sequential_20 expects 1 inputs, but it received 2 input tensors

Question

I am trying to build a simple Autoencoder using the KMNIST dataset from Tensorflow and some sample code from a textbook I'm using, but I keep getting an error when I try to fit the model.

The error says ValueError: Layer sequential_20 expects 1 inputs, but it received 2 input tensors.

I'm really new to TensorFlow, and all my research on this error has baffled me since it seems to involve things not in my code. This thread wasn't helpful since I'm only using sequential layers.

Code in full:

import numpy as np
import tensorflow as tf
from tensorflow import keras
import tensorflow_datasets as tfds
import pandas as pd
import matplotlib.pyplot as plt

#data = tfds.load(name = 'kmnist')

(img_train, label_train), (img_test, label_test) = tfds.as_numpy(tfds.load(
    name = 'kmnist',
    split=['train', 'test'],
    batch_size=-1,
    as_supervised=True,
))

img_train = img_train.squeeze()
img_test = img_test.squeeze()

## From Hands on Machine Learning Textbook, chapter 17

stacked_encoder = keras.models.Sequential([
    keras.layers.Flatten(input_shape=[28, 28]),
    keras.layers.Dense(100, activation="selu"),
    keras.layers.Dense(30, activation="selu"),
])

stacked_decoder = keras.models.Sequential([
    keras.layers.Dense(100, activation="selu", input_shape=[30]),
    keras.layers.Dense(28 * 28, activation="sigmoid"),
    keras.layers.Reshape([28, 28])
])

stacked_ae = keras.models.Sequential([stacked_encoder, stacked_decoder])
stacked_ae.compile(loss="binary_crossentropy",
                   optimizer=keras.optimizers.SGD(lr=1.5))

history = stacked_ae.fit(img_train, img_train, epochs=10,
                         validation_data=[img_test, img_test])

Marco Cerliani · Accepted Answer · 2020-08-26 21:57:37Z

36

it helped me when I changed:
validation_data=[X_val, y_val] into validation_data=(X_val, y_val)
Actually still wonder why?

edited Aug 26, 2020 at 21:57

Marco Cerliani

22.1k3 gold badges58 silver badges61 bronze badges

answered May 5, 2020 at 12:54

easy_rider

3632 silver badges5 bronze badges

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

Comments

kitokid · Accepted Answer · 2021-02-23 15:01:08Z

15

As stated in the Keras API reference (link),

validation_data: ... validation_data could be: - tuple (x_val, y_val) of Numpy arrays or tensors - tuple (x_val, y_val, val_sample_weights) of Numpy arrays - dataset ...

So, validation_data has to be a tuple rather than a list (of Numpy arrays or tensors). We should use parentheses (round brackets) (...), not square brackets [...].

According to my limited experience, however, TensorFlow 2.0.0 would be indifferent to the use of square brackets, but TensorFlow 2.3.0 would complain about it. Your script would be fine if it is run under TF 2.0 intead of TF 2.3.

edited Feb 23, 2021 at 15:01

kitokid

3,12718 gold badges67 silver badges104 bronze badges

answered Aug 26, 2020 at 19:14

Li-Pin Juan

1,2551 gold badge16 silver badges24 bronze badges

1 Comment

Euler_Salter Over a year ago

I was using Google Colab and I got the same error in the question. Typing %tensorflow version 2.x fixed the tensorflow version to 2.0 rather than 2.3 and then it worked! (using ( rather than [). How do you fix this when using tensorflow 2.3? Simply changing parenthesis didn't work with tf 2.3

Marco Cerliani · Accepted Answer · 2021-03-03 08:09:14Z

15

Use validation_data=(img_test, img_test) instead of validation_data=[img_test, img_test]

Here the example with encoder and decoder combined together:

stacked_ae = keras.models.Sequential([
    keras.layers.Flatten(input_shape=[28, 28]),
    keras.layers.Dense(100, activation="selu"),
    keras.layers.Dense(30, activation="selu"),
    keras.layers.Dense(100, activation="selu"),
    keras.layers.Dense(28 * 28, activation="sigmoid"),
    keras.layers.Reshape([28, 28])
])

stacked_ae.compile(loss="binary_crossentropy",
                   optimizer=keras.optimizers.SGD(lr=1.5))

history = stacked_ae.fit(img_train, img_train, epochs=10,
                         validation_data=(img_test, img_test))

edited Mar 3, 2021 at 8:09

answered May 4, 2020 at 7:57

Marco Cerliani

22.1k3 gold badges58 silver badges61 bronze badges

Comments

xmantas · Accepted Answer · 2021-02-20 15:48:09Z

2

You have given data instead of labels two times:

history = stacked_ae.fit(img_train, img_train, epochs=10,
                         validation_data=[img_test, img_test])

instead of

history = stacked_ae.fit(img_train, label_train, epochs=10,
                         validation_data=[img_test, label_test])

answered Feb 20, 2021 at 15:48

xmantas

5985 silver badges11 bronze badges

2 Comments

kitokid Over a year ago

This is autoencoder which is semi-supervised, not typical ML problem. that's why no need to pass separate labels.

user12587364 Over a year ago

But this is autoencoder, so labels are not passed at model fit.

Mehmet Burak Sayıcı · Accepted Answer · 2021-07-05 23:42:56Z

1

In solutions, some says you need to change from bracelet to parentheses, but it was not working in Colab. And yes, turningvalidation_data=[X_val, y_val] into validation_data=(X_val, y_val) should work since it's required format, but in tf==2.5.0(in Google Colab) it doesn't solve the problem. I changed from functional API to sequential API, that solves the problem. Strange.

answered Jul 5, 2021 at 23:42

Mehmet Burak Sayıcı

4671 gold badge5 silver badges14 bronze badges

Comments

Skippy le Grand Gourou · Accepted Answer · 2023-01-16 20:10:59Z

0

This error may also be triggered by submitting the wrong object to model.fit(). It happened to me when I mistakenly tried to execute

model.fit(images)

when I wanted to execute

model.fit(dataset)

with

dataset = tf.data.Dataset.from_tensor_slices((images, images))

answered Jan 16, 2023 at 20:10

Skippy le Grand Gourou

7,8626 gold badges66 silver badges82 bronze badges

Collectives™ on Stack Overflow

ValueError: Layer sequential_20 expects 1 inputs, but it received 2 input tensors

6 Answers 6

Comments

1 Comment

Comments

2 Comments

Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

6 Answers 6

Comments

1 Comment

Comments

2 Comments

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related