ValueError: Error when checking input: expected conv1d_29_input to have 3 dimensions, but got array with shape (150, 1320)

user_5653423 0
Viewed 95
momentum_rate = 0.5
learning_rate = 0.1
neurons = 30

def convolutional_neural_network(x, y):
    print("Hyper-parameter values:\n")
    print('Momentum Rate =',momentum_rate,'\n')
    print('learning rate =',learning_rate,'\n')
    print('Number of neurons =',neurons,'\n')
    model = Sequential()
    #model.summary()
    model.add(Conv1D(input_shape=(X.shape[1],X.shape[0]),activation='relu',kernel_size = 1,filters = 64))
    
    model.add(Flatten())
    
    model.add(Dense(neurons,activation='relu')) # first hidden layer
    model.summary()
    model.add(Dense(neurons, activation='relu'))
    model.summary()# second hidden layer
    model.add(Dense(neurons, activation='relu'))
    model.summary()
    model.add(Dense(neurons, activation='relu'))
    model.summary()
    model.add(Dense(10, activation='softmax'))
    model.summary()
    sgd = optimizers.SGD(lr=learning_rate, decay=1e-6, momentum=momentum_rate, nesterov=True)
    model.summary()
    model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy',tensorflow.keras.metrics.Precision()])
    model.summary()
    history = model.fit(X, y, validation_split=0.2, epochs=10)
    model.summary()
    print("\nTraining Data Statistics:\n")
    print("CNN Model with Relu Hidden Units and Cross-Entropy Error Function:")

print(convolutional_neural_network(X,y))

The shape of X is (150, 1320) The shape of y is (150,)

Here is the output I am getting:

Model: "sequential_36"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1d_30 (Conv1D)           (None, 1320, 64)          9664      
_________________________________________________________________
flatten_21 (Flatten)         (None, 84480)             0         
_________________________________________________________________
dense_106 (Dense)            (None, 30)                2534430   
_________________________________________________________________
dense_107 (Dense)            (None, 30)                930       
_________________________________________________________________
dense_108 (Dense)            (None, 30)                930       
_________________________________________________________________
dense_109 (Dense)            (None, 30)                930       
_________________________________________________________________
dense_110 (Dense)            (None, 10)                310       
=================================================================
Total params: 2,547,194
Trainable params: 2,547,194
Non-trainable params: 0

ValueError: Error when checking input: expected conv1d_30_input to have 3 dimensions, but got array with shape (150, 1320)
conv-neural-network tensorflow python
2 Answers

Conv1D is expecting an input_shape of the form (steps, input_dim) (see docs). Now, if I understand correctly your input_dim=1 because 1320 is the number of samples and 150 the length of the array. In this case, change the input_shape=(X.shape[1], X.shape[2]).

Edit: It's unclear what are you trying to do. The code below is working and shows the expected shapes for your network. But beware that I changed the y dimension in order to match the number of rows and the output layer. I'm not sure of what the y shape (150,) is representing.

X = tf.random.normal((1320,150,1))
y = tf.random.uniform((1320,10))

momentum_rate = 0.5
learning_rate = 0.1
neurons = 30

def convolutional_neural_network(x, y):
    print("Hyper-parameter values:\n")
    print('Momentum Rate =',momentum_rate,'\n')
    print('learning rate =',learning_rate,'\n')
    print('Number of neurons =',neurons,'\n')
    model = Sequential()
    #model.summary()
    model.add(Conv1D(input_shape=(X.shape[1], X.shape[2]),activation='relu',kernel_size = 1,filters = 64))
    
    model.add(Flatten())
    
    model.add(Dense(neurons,activation='relu')) # first hidden layer
    model.add(Dense(neurons, activation='relu'))
    model.add(Dense(neurons, activation='relu'))
    model.add(Dense(neurons, activation='relu'))
    model.add(Dense(10, activation='softmax'))
    sgd = optimizers.SGD(lr=learning_rate, decay=1e-6, momentum=momentum_rate, nesterov=True)
    model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'] )
    history = model.fit(X, y, validation_split=0.2, epochs=10)
    model.summary()
    print("\nTraining Data Statistics:\n")
    print("CNN Model with Relu Hidden Units and Cross-Entropy Error Function:")

print(convolutional_neural_network(X,y))
user_162435740

As your error reflects your input shape is (150, 1320). In the comment you have said you have 1320 samples (row) and 150 features (column).

Let's make some temp data with mentioned shapes as X and y:

X = tf.random.uniform((150,1320))
y = tf.random.uniform((1320,10))  
#10 label for each sample which maybe a little strange, take care of it

Now we have X with shape (150,1320) and y with shape (1320,10).

Since we have 1320 samples and it should be the first axis, we have to transpose it:

X = tf.transpose(X)

Now the X shape will be (1320,150) instead of (150,1320).

Since a Conv1D layer expects input as batch_shape + (steps, input_dim), we need to add a new dimension. So:

X = tf.expand_dims(X,axis=2)
print(X.shape, y.shape)     # X.shape=(1320, 150, 1) y.shape=(1320,10)

Then, we have X shape as (1320,150,1)

Now, let's specify the input shape in the Conv1D layer:

model.add(Conv1D(input_shape=(X.shape[1:]),activation='relu',kernel_size = 1,filters = 64))
user_24232780
Related