CODEWITHSUNDEEP
tensorflowkerasscikit-learndeep-learning
Maryam Anwer
Maryam Anwer

Reputation: 43

Keras neural network prediction not working

I have created a project using keras and tensorflow. I used the NSL KDD dataset and coded my project in python. I also used the SGD optimizer.

I would like to fit a model then evaluate it and then check its accuracy. (So I can compare it to the results with machine learning).

Here is my complete code below, please review it.

import tensorflow as tf
from keras import backend as K

from tensorflow.python.saved_model import builder as saved_model_builder
from tensorflow.python.saved_model import tag_constants, signature_constants, signature_def_utils_impl

from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD
import numpy as np
sess = tf.Session()
K.set_session(sess)
K.set_learning_phase(0)
model_version = "2"


import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('KDD_Dataset.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 41:42].values
# Encoding categorical data X
from sklearn.preprocessing import LabelEncoder
labelencoder_X = LabelEncoder()
X[:,0] = labelencoder_X.fit_transform(X[:,0])
X[:,1] = labelencoder_X.fit_transform(X[:,1])
X[:,2] = labelencoder_X.fit_transform(X[:,2])
#
from sklearn.preprocessing import OneHotEncoder
onehotencoder_0 = OneHotEncoder(categorical_features=[0])
onehotencoder_1 = OneHotEncoder(categorical_features=[1])
onehotencoder_2 = OneHotEncoder(categorical_features=[2])
X = onehotencoder_0.fit_transform(X).toarray()
X = onehotencoder_1.fit_transform(X).toarray()
X = onehotencoder_2.fit_transform(X).toarray()

# Encoding categorical data y
from sklearn.preprocessing import LabelEncoder
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)
max(y)

# Splitting the dataset into the Training set and Test set
#from sklearn.cross_validation import train_test_split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, 
                                                    test_size = 0.2, 
                                                    random_state = 0)
# create the model
model = Sequential()
model.add(Dense(41, input_dim=8, init='uniform', activation='relu'))
model.add(Dense(20, init='uniform', activation='relu'))
model.add(Dense(1, init='uniform', activation='sigmoid'))
# compile the model

model.compile(loss='binary_crossentropy', optimizer=sgd,metrics=['accuracy'])

model.fit(X_train, y_train, validation_data=(X_test, y_test), nb_epoch=200, batch_size=5, verbose=0)

Upvotes: 0

Views: 315

Answers (2)

Messias Alves
Messias Alves

Reputation: 1

Change line

model.add(Dense(41, input_dim=8, init='uniform', activation='relu'))

to

model.add(Dense(42, input_dim=42, init='uniform', activation='relu'))

and

optimizer=sgd to optimizer='sgd'

Upvotes: 0

George Yu
George Yu

Reputation: 134

See Dense(41, input_dim=8, init='uniform', activation='relu') The model you defined with 8 features, however your inputs have 45 features. They are not matching. You have to either make your model with 45 features to match the input, or cut the length of input feature to 8 to match your model.

Upvotes: 1

Related Questions