Keras - Error when checking target

Question

Given the following code:

import matplotlib.pyplot as plt
import numpy
from keras import callbacks
from keras import optimizers
from keras.layers import Dense, Dropout
from keras.models import Sequential
from keras.callbacks import ModelCheckpoint
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import ExtraTreesClassifier

from sklearn.utils import shuffle

# Early stopping - Stop training before overfitting
early_stop = callbacks.EarlyStopping(monitor='val_loss', min_delta=0, patience=3, verbose=1, mode='auto')

# fix random seed for reproducibility
seed = 42
numpy.random.seed(seed)
# load pima indians dataset
dataset = numpy.loadtxt("./data/poc.csv",skiprows=1, delimiter=",")
# split into input (X) and output (Y) variables
X = dataset[:, 0:14]
Y = dataset[:, 14:18]

# # Standardize features by removing the mean and scaling to unit variance
scaler = StandardScaler()
X = scaler.fit_transform(X)


#ADAM Optimizer with learning rate decay
opt = optimizers.Adam(lr=0.0001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0001)

## Create our model
model = Sequential()

model.add(Dense(200, input_dim=14, kernel_initializer='uniform', activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(60, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(30, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(5, activation='sigmoid'))


model.summary()
# Compile the model using binary crossentropy since we are predicting 0/1
model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])

# checkpoint
filepath="./checkpoints/weights.best.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')

# Fit the model
history = model.fit(X, Y, validation_split=0.33, epochs=10000, batch_size=10, verbose=0, callbacks=[early_stop,checkpoint])

And Data like so:

17.6,1,1,0,1,0,0,0,0,0,0,3.9,9.2,20.29,0,1,0,0,0
12.9,1,0,1,0,0,0,0,0,0,0,4.1,13.5,0.08,0,0,0,1,0
3.2,1,0,1,0,0,0,0,0,0,0,4.122031746,13.8,0.01,0,0,0,0,0
...

I get the following output / error:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              (None, 200)               3000      
_________________________________________________________________
dropout_1 (Dropout)          (None, 200)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 100)               20100     
_________________________________________________________________
dropout_2 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_3 (Dense)              (None, 60)                6060      
_________________________________________________________________
dropout_3 (Dropout)          (None, 60)                0         
_________________________________________________________________
dense_4 (Dense)              (None, 30)                1830      
_________________________________________________________________
dropout_4 (Dropout)          (None, 30)                0         
_________________________________________________________________
dense_5 (Dense)              (None, 5)                 155       
=================================================================
Total params: 31,145
Trainable params: 31,145
Non-trainable params: 0
_________________________________________________________________

Error when checking target: expected dense_5 to have shape (None, 1) but got array with shape (716, 4)

What am I missing?

Answer 1

Your last layer, dense_5, has size 5, while your target has size 4.

In order to work, the size of each targert must be the number of classes you want to predict. Remember that they have to be represented in one hot enconding. You can use to_categorical from Keras.