CODEWITHSUNDEEP
pythonmachine-learningkerasneural-network
xabash
xabash

Reputation: 9

Keras Sequential model loss won't decrease & remains constant through all epochs

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
df = pd.read_csv('insurance.csv')
X = df.drop(['sex', 'children', 'smoker', 'region'], axis = 1)
X = X.values
y = df['charges']
y = y.values.reshape(1331,1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 75)
from keras import Sequential
from keras.layers import Dense
model = Sequential()
model.add(Dense(5, activation = 'sigmoid'))
model.add(Dense(4, activation = 'sigmoid'))
model.add(Dense(1, activation = 'sigmoid'))
from keras import optimizers
sgd = optimizers.SGD(lr=0.1)
model.compile(sgd, 'mse')
model.fit(X_train, y_train, 32, 100, shuffle=False)

This right here is my code, the data I am feeding in is all numerical, and I have tried different hyperparameters, nothing seems to work. Any help would be much appreciated. I just don't know what is going wrong over here.

Upvotes: 0

Views: 133

Answers (1)

desertnaut
desertnaut

Reputation: 60400

If you are indeed in a regression setting (as implied by your choice of loss, MSE) and not in a classification one, the basic mistake in your code is the activation of your last layer, which should be linear:

model.add(Dense(1, activation = 'linear'))

Of course, there can be several other things going wrong with your approach, including the architecture of your model itself (there is not any kind of "guarantee" that, whatever model architecture you throw in your data, it will produce decent results, and your model looks too simple), the activation functions of the other layers (usually today we start with relu) etc., but it is impossible to say more without knowing your data.

Upvotes: 1

Related Questions