ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (999, 12, 1) while fitting with model

Question

I am working on building a 2d convolution network on my dataset.I was running it on a test set with code below :

#reproducible code
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.utils import np_utils
from keras import optimizers
from sklearn.metrics import confusion_matrix
import numpy as np
import time
from keras.layers.convolutional import Conv2D

data = np.random.rand(1000,22)
data.shape
train_X = data[0:data.shape[0],0:12]
train_X.shape
train_y = data[0:data.shape[0],12:data.shape[1]]
train_y.shape
train_X = train_X.reshape((train_X.shape[0], train_X.shape[1], 1))
train_X.shape
neurons = 10
model = Sequential()
model.add(Conv2D(filters=64,input_shape=train_X.shape, activation='relu',kernel_size = 3))
model.add(Flatten())
model.add(Dense(neurons,activation='relu')) # first hidden layer
model.add(Dense(neurons, activation='relu')) # second hidden layer
model.add(Dense(neurons, activation='relu')) # third hidden layer
model.add(Dense(10, activation='softmax'))
sgd = optimizers.SGD(lr=0.05, decay=1e-6, momentum=0.95, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
model.summary()
model.fit(train_X,train_y, validation_split=0.2, epochs=10, batch_size=100, verbose=0)
model.summary()

My model runs for a while and shows the following summary :

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #
================================================================= 
conv2d_1 (Conv2D)            (None, 997, 10, 64)       640       
_________________________________________________________________
flatten_1 (Flatten)          (None, 638080)            0
_________________________________________________________________
dense_1 (Dense)              (None, 10)                6380810
_________________________________________________________________
dense_2 (Dense)              (None, 10)                110
_________________________________________________________________
dense_3 (Dense)              (None, 10)                110
_________________________________________________________________
dense_4 (Dense)              (None, 10)                110
=================================================================
Total params: 6,381,780
Trainable params: 6,381,780
Non-trainable params: 0

It gets stuck at the model.fit and throws up the error shown below.I am wondering how to solve this error.

Traceback (most recent call last):
  File "CNN_test.py", line 65, in <module>
    model.fit(train_X,train_y, validation_split=0.2, epochs=10, batch_size=100, verbose=0)
  File "/usr/local/lib/python3.6/site-packages/keras/engine/training.py", line 1154, in fit
    batch_size=batch_size)
  File "/usr/local/lib/python3.6/site-packages/keras/engine/training.py", line 579, in _standardize_user_data
    exception_prefix='input')
  File "/usr/local/lib/python3.6/site-packages/keras/engine/training_utils.py", line 135, in standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (999, 12, 1)

Nicolas Gervais · Accepted Answer · 2020-08-08 07:42:15Z

You have no reason to use 2D convolutional layers since your data is 3D. What you're looking for is Conv1D. Also, don't include the n_samples dimension in input_shape.

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv1D, Flatten
from tensorflow.keras import optimizers
import numpy as np

data = np.random.rand(1000,22)

train_X = data[0:data.shape[0],0:12]
train_X = train_X.reshape((train_X.shape[0], train_X.shape[1], 1))

train_y = data[0:data.shape[0],12:data.shape[1]]

neurons = 10
model = Sequential()
model.add(Conv1D(filters=64,input_shape=train_X.shape[1:], 
    activation='relu',kernel_size = 3))
model.add(Flatten())
model.add(Dense(neurons,activation='relu')) # first hidden layer
model.add(Dense(10, activation='softmax'))
sgd = optimizers.SGD(lr=0.05, decay=1e-6, momentum=0.95, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
history = model.fit(train_X, train_y, validation_split=0.2, epochs=1, batch_size=100)

Train on 800 samples, validate on 200 samples
100/800 [==>...........................] - ETA: 2s - loss: 11.4786 - acc: 0.0800
800/800 [==============================] - 0s 547us/sample - loss: 55.3883 - acc: 0.1000

Tabaene Haque · Accepted Answer · 2020-08-08 07:14:07Z

0

You need train_X to have a fourth dimension. Just like the error message says.

train_X = train_X.reshape(train_X.shape[0], train_X.shape[1], 1, 1)

edited Aug 8, 2020 at 7:14

answered Aug 8, 2020 at 7:10

Tabaene Haque

5742 silver badges10 bronze badges

3 Comments

user12868543 Over a year ago

It leads to error at model.add stage itself: showing ValueError: Input 0 is incompatible with layer conv2d_1: expected ndim=4, found ndim=5

Tabaene Haque Over a year ago

The problem is input_shape=train_X.shape. It should actually contain 3 dimensions only. And internally keras will add the batch dimension making it 4. Since you probably used input_shape (train_X.shape) with 4 dimensions (batch included), keras is adding the 5th.

user12868543 Over a year ago

I just checked train_X.shape is (1000, 12, 1)

Collectives™ on Stack Overflow

ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (999, 12, 1) while fitting with model

2 Answers 2

Comments

3 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

3 Comments

Your Answer

Sign up or log in

Post as a guest

Related