CODEWITHSUNDEEP
pythontensorflowkerasdeep-learningconv-neural-network
Panri93
Panri93

Reputation: 213

Keras: Error when checking input of cnn model

I'm trying to create a CNN model for image classification, however, I'm getting an error with the input shape and I don´t understand why. Please, see below the code:

import pandas as pd
from keras_preprocessing.image import ImageDataGenerator
import numpy as np

#CREATING 3 DATAFRAMES FROM 3 .TXT FILES
trainingfile = pd.read_table('data/training.txt', delim_whitespace=True, names=('class', 'image'))
testingfile = pd.read_table('data/testing.txt', delim_whitespace=True, names=('class', 'image'))
validationfile = pd.read_table('data/validation.txt', delim_whitespace=True, names=('class', 'image'))
# CHANGING TYPE OF TARGET ATTRIBUTE
trainingfile = trainingfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])
testingfile = testingfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])
validationfile = validationfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])

#DATA AUGMENTATION
datagen=ImageDataGenerator()
train_datagen = ImageDataGenerator( 
    rotation_range=5,
    zoom_range=0.1)

#Generating train, test and validation datasets with RGB, Batch = 32.
train=train_datagen.flow_from_dataframe(dataframe=trainingfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256),color_mode='rgb',batch_size=32)
test=datagen.flow_from_dataframe(dataframe=testingfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256),color_mode='rgb',batch_size=32)
#No data augmentation to the validation set
validation=datagen.flow_from_dataframe(dataframe=validationfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256),color_mode='rgb', batch_size=32)

And now is when I start designing the CNN model:

from keras.models import Sequential
from keras.layers import Dense, Conv2D, Flatten, Activation, Dropout, MaxPooling2D, BatchNormalization
from keras.constraints import maxnorm

#CNN model
model = Sequential()
model.add(Conv2D(32, kernel_size = (3, 3), activation='relu', input_shape=(32, 250, 250, 3)))

As you can see the input_shape is 32 (batch), 250 x 250 image size and 3 channels because of RGB. However, I get the following error:

ValueError: Input 0 is incompatible with layer conv2d_1: expected ndim=4, found ndim=5

Upvotes: 0

Views: 280

Answers (2)

Pedrolarben
Pedrolarben

Reputation: 1235

The problem is the input_shape of the Conv2D layer, you don't have to set the batch size. Change input_shape=(32, 250, 250, 3) to input_shape=(250, 250, 3).

Upvotes: 1

jkr
jkr

Reputation: 19310

The input_shape in the convolutional layer should not include the batch dimension. Here's an excerpt from the Keras documentation:

When using [Conv2D] as the first layer in a model, provide the keyword argument input_shape (tuple of integers, does not include the sample axis), e.g. input_shape=(128, 128, 3) for 128x128 RGB pictures in data_format="channels_last".

So the solution would be to change your model definition, as below. You had another error in the input_shape -- it should be 256x256x3, not 250x250x3.

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(256, 256, 3)))

You do not need to specify the batch size explicitly in the model definition because it can vary.

Upvotes: 1

Related Questions