Keras Input Layer Shape On Input Layer Error

Question

I am trying to learn ai algorithms by building. I found a question on Stackoverflow which is here. I copied this code to try it out, and then modified it to this.

import numpy as np
import tensorflow as tf
from tensorflow import keras as keras
from tensorflow.keras.layers import Dense, Activation
from tensorflow.keras.models import Sequential
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from tensorflow.python.keras import activations
# Importing the dataset
dataset = np.genfromtxt("data.txt", delimiter='')
X = dataset[:, :-1]
y = dataset[:, -1]

# Splitting the dataset into the Training set and Test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.08, random_state = 0)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)



# Initialising the ANN
#model = Sequential()

# Adding the input layer and the first hidden layer
#model.add(Dense(32, activation = 'relu', input_dim = 6))

# Adding the second hidden layer
#model.add(Dense(units = 32, activation = 'relu'))

# Adding the third hidden layer
#model.add(Dense(units = 32, activation = 'relu'))

# Adding the output layer

#model.add(Dense(units = 1))
#model = Sequential([
#    keras.Input(shape= (6),name= "digits"),
#    Dense(units = 32, activation = "relu"),
#    Dense(units = 32, activation = "relu"),
#    Dense(units = 1 , name = "predict")##

#])
#
input = keras.Input(shape= (6),name= "digits")
#x0 = Dense(units = 6)(input)
x1 = Dense(units = 32, activation = "relu")(input)
x2 = Dense(units = 32, activation = "relu")(x1)
output = Dense(units = 1 , name = "predict")(x2)

model = keras.Model(inputs = input , outputs= output)
#model.add(Dense(1))
# Compiling the ANN
#model.compile(optimizer = 'adam', loss = 'mean_squared_error')

# Fitting the ANN to the Training set
#model.fit(X_train, y_train, batch_size = 10, epochs = 200)

optimizer = keras.optimizers.Adam(learning_rate=1e-3)
loss = keras.losses.MeanSquaredError()

epochs = 200

for epoch in range(epochs):
    print("\nStart of epoch %d" % (epoch,))

    # Iterate over the batches of the dataset.
    for step in range(len(X_train)):

        # Open a GradientTape to record the operations run
        # during the forward pass, which enables auto-differentiation.
        with tf.GradientTape() as tape:

            # Run the forward pass of the layer.
            # The operations that the layer applies
            # to its inputs are going to be recorded
            # on the GradientTape.
            logits = model( X_train[step] , training=True)  # Logits for this minibatch

            # Compute the loss value for this minibatch.
            loss_value = loss(y_train[step], logits)

        # Use the gradient tape to automatically retrieve
        # the gradients of the trainable variables with respect to the loss.
        grads = tape.gradient(loss_value, model.trainable_weights)

        # Run one step of gradient descent by updating
        # the value of the variables to minimize the loss.
        optimizer.apply_gradients(zip(grads, model.trainable_weights))

        # Log every 200 batches.
        if step % 200 == 0:
            print(
                "Training loss (for one batch) at step %d: %.4f"
                % (step, float(loss_value))
            )
            print("Seen so far: %s samples" % ((step + 1) * 64))


y_pred = model.predict(X_test)

plt.plot(y_test, color = 'red', label = 'Real data')
plt.plot(y_pred, color = 'blue', label = 'Predicted data')
plt.title('Prediction')
plt.legend()
plt.show()

I modified the code for creating data when processing. If I use model.fit, it uses data I have given but I wanted to when epochs start to create data from a simulation and then process it.(sorry for bad english. if i couldn't explain very well)

When I start code in line 81:

Exception has occurred: ValueError
Input 0 of layer dense is incompatible with the layer: : expected min_ndim=2, found ndim=1. Full shape received: (6,)

It gives an Exception. I tried to use shape=(6,) shape=(6,1) or similar to this but it doesn't fix anything.

Answer 1

You need to add a batch dimension when calling the keras model:

logits = model( X_train[step][np.newaxis,:] , training=True)  # Logits for this minibatch

A batch dimension is used to feed multiple samples to the network. By default, Keras assumes that the input has a batch dimension. To feed one sample, Keras expects a batch of 1 sample. In that case, it means a shape of (1,6). If you want to feed a batch of 2 samples, then the shape will be (2,6), etc.