How to evaluate a keras model?

How to evaluate a keras model?

How to evaluate a keras model?

This recipe helps you evaluate a keras model


Recipe Objective

In machine learning, We have to first train the model and then we have to check that if the model is working properly or not. Does the model is efficient or not to predict further result.
We can evaluate the model by various metrics like accuracy, f1 score, etc.

So this recipe is a short example of how to evaluate a keras model?

Step 1 - Import the library

import pandas as pd import numpy as np from keras.datasets import mnist from sklearn.model_selection import train_test_split from keras.models import Sequential from keras.layers import Dense from keras.layers import Dropout

We have imported pandas, numpy, mnist(which is the dataset), train_test_split, Sequential, Dense and Dropout. We will use these later in the recipe.

Step 2 - Loading the Dataset

Here we have used the inbuilt mnist dataset and stored the train data in X_train and y_train. We have used X_test and y_test to store the test data. (X_train, y_train), (X_test, y_test) = mnist.load_data()

Step 3 - Creating model and adding layers

We have created an object model for sequential model. We can use two args i.e layers and name. model = Sequential() Now, We are adding the layers by using 'add'. We can specify the type of layer, activation function to be used and many other things while adding the layer.
Here we have added four layers which will be connected one after other. model.add(Dense(512)) model.add(Dropout(0.3)) model.add(Dense(256, activation='relu')) model.add(Dropout(0.2))

Step 4 - Compiling the model

We can compile a model by using compile attribute. Let us first look at its parameters before using it.

  • optimizer : In this we can pass the optimizer we want to use. There are various optimizer like SGD, Adam etc.
  • loss : In this we can pass a loss function which we want for the model
  • metrics : In this we can pass the metric on which we want the model to be scored
model.compile(optimizer='Adam', loss='categorical_crossentropy', metrics=['accuracy'])

Step 5 - Fitting the model

We can fit a model on the data we have and can use the model after that. Here we are using the data which we have split i.e the training data for fitting the model.
While fitting we can pass various parameters like batch_size, epochs, verbose, validation_data and so on., y_train, batch_size=128, epochs=2, verbose=1, validation_data=(X_test, y_test)

Step 6 - Evaluating the model

After fitting a model we want to evaluate the model. Here we are using model.evaluate to evaluate the model and it will give us the loss and the accuracy. Here we have also printed the score. score = model.evaluate(X_test, y_test, verbose=0) print('Test loss:', score[0]) print('Test accuracy:', score[1]) As an output we get:

Epoch 1/2
469/469 [==============================] - 6s 14ms/step - loss: 0.3202 - accuracy: 0.9022 - val_loss: 0.1265 - val_accuracy: 0.9610
Epoch 2/2
469/469 [==============================] - 6s 14ms/step - loss: 0.1542 - accuracy: 0.9541 - val_loss: 0.0916 - val_accuracy: 0.9718
Test loss: 0.09163221716880798
Test accuracy: 0.9718000292778015

Relevant Projects

Data Science Project in Python on BigMart Sales Prediction
The goal of this data science project is to build a predictive model and find out the sales of each product at a given Big Mart store.

Sequence Classification with LSTM RNN in Python with Keras
In this project, we are going to work on Sequence to Sequence Prediction using IMDB Movie Review Dataset​ using Keras in Python.

Predict Credit Default | Give Me Some Credit Kaggle
In this data science project, you will predict borrowers chance of defaulting on credit loans by building a credit score prediction model.

Data Science Project on Wine Quality Prediction in R
In this R data science project, we will explore wine dataset to assess red wine quality. The objective of this data science project is to explore which chemical properties will influence the quality of red wines.

Mercari Price Suggestion Challenge Data Science Project
Data Science Project in Python- Build a machine learning algorithm that automatically suggests the right product prices.

Human Activity Recognition Using Multiclass Classification in Python
In this human activity recognition project, we use multiclass classification machine learning techniques to analyse fitness dataset from a smartphone tracker.

Predict Macro Economic Trends using Kaggle Financial Dataset
In this machine learning project, you will uncover the predictive value in an uncertain world by using various artificial intelligence, machine learning, advanced regression and feature transformation techniques.

Resume parsing with Machine learning - NLP with Python OCR and Spacy
In this machine learning resume parser example we use the popular Spacy NLP python library for OCR and text classification.

Machine Learning or Predictive Models in IoT - Energy Prediction Use Case
In this machine learning and IoT project, we are going to test out the experimental data using various predictive models and train the models and break the energy usage.

Data Science Project - Instacart Market Basket Analysis
Data Science Project - Build a recommendation engine which will predict the products to be purchased by an Instacart consumer again.