Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 299 views

    Cat and Dog Classification Using CNN: Project Objective

    Uploaded by

    coursera details
    This document describes building a convolutional neural network (CNN) model to classify images of cats and dogs. The model is trained on a dataset of cat and dog images and calculates an accuracy score on test data. It provides details on importing necessary libraries, initializing and compiling the CNN model, performing image augmentation, and processing images through convolution, activation, pooling and fully connected layers. The trained model can then be used to predict new images as either cats or dogs based on the probability output.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Cat and Dog Classification Using CNN: Project Objective

    Uploaded by

    coursera details
    299 views7 pages
    This document describes building a convolutional neural network (CNN) model to classify images of cats and dogs. The model is trained on a dataset of cat and dog images and calculates an accuracy score on test data. It provides details on importing necessary libraries, initializing and compiling the CNN model, performing image augmentation, and processing images through convolution, activation, pooling and fully connected layers. The trained model can then be used to predict new images as either cats or dogs based on the probability output.

    Original Title

    cat_vs_dog_classification

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document describes building a convolutional neural network (CNN) model to classify images of cats and dogs. The model is trained on a dataset of cat and dog images and calculates an accuracy score on test data. It provides details on importing necessary libraries, initializing and compiling the CNN model, performing image augmentation, and processing images through convolution, activation, pooling and fully connected layers. The trained model can then be used to predict new images as either cats or dogs based on the probability output.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    299 views7 pages

    Cat and Dog Classification Using CNN: Project Objective

    Uploaded by

    coursera details
    This document describes building a convolutional neural network (CNN) model to classify images of cats and dogs. The model is trained on a dataset of cat and dog images and calculates an accuracy score on test data. It provides details on importing necessary libraries, initializing and compiling the CNN model, performing image augmentation, and processing images through convolution, activation, pooling and fully connected layers. The trained model can then be used to predict new images as either cats or dogs based on the probability output.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 7

    Cat and dog classification using CNN

    Project Objective:

    Build a CNN model that classifies the given pet images correctly into dog and cat images.
    The project scope document specifies the requirements for the project “Pet Classification Model Using
    CNN.” Apart from specifying the functional and non-functional requirements for the project, it also
    serves as an input for project scoping.
    Project Description and Scope:
    You are provided with a collection of images of pets, that is, cats and dogs. These images are of different
    sizes with varied lighting conditions and they should be used as inputs for your model.
    You are expected to write the code for CNN image classification model using TensorFlow that trains on the
    data and calculates the accuracy score on the test data.
    Starting the Projects:
    Convolutional Neural Network (CNN) is an algorithm taking an image as input then assigning weights
    and biases to all the aspects of an image and thus differentiates one from the other. Neural networks
    can be trained by using batches of images, each of them having a label to identify the real nature of
    the image (cat or dog here). A batch can contain few tenths to hundreds of images. For each image,
    the network prediction is compared with the corresponding existing label, and the distance between
    network prediction and the truth is evaluated for the whole batch. Then, the network parameters are
    modified to minimize the distance and thus the prediction capability of the network is increased. The
    training process continues for every batch similarly.

    Dogs vs. Cats Prediction Problem

    The main goal is to develop a system that can identify images of cats and dogs. The input image will
    be analysed and then the output is predicted. The model that is implemented can be extended to a
    website or any mobile device as per the need. The dataset contains a set of images of cats and dogs.
    Cat and dog classification using CNN
    Our main aim here is for the model to learn various distinctive features of cat and dog. Once the
    training of the model is done it will be able to differentiate images of cat and dog.

    Import Libraries
    NumPy- For working with arrays, linear algebra.

    2. Pandas – For reading/writing data

    3. Matplotlib – to display images

    4. TensorFlow Keras models – Need a model to predict right !!

    5. TensorFlow Keras layers – Every NN needs layers and CNN needs well a couple of layers.

    CNN does the processing of Images with the help of matrixes of weights known as filters. They detect
    low-level features like vertical and horizontal edges etc. Through each layer, the filters recognize
    high-level features.

    We first initialize the CNN


    Cat and dog classification using CNN
    For compiling the CNN, we are using adam optimizer.
    Adaptive Moment Estimation (Adam) is a method used for computing individual learning
    rates for each parameter. For loss function, we are using Binary cross-entropy to compare the
    class output to each of the predicted probabilities. Then it calculates the penalization score
    based on the total distance from the expected value.
    Image augmentation is a method of applying different kinds of transformation to original
    images resulting in multiple transformed copies of the same image. The images are different
    from each other in certain aspects because of shifting, rotating, flipping techniques. So, we
    are using the Keras ImageDataGenerator class to augment our images.

    To check your images with


    ImageDataGenerotor Model

    We need a way to turn our images into batches of data arrays in memory so that they can be fed to the
    network during training. ImageDataGenerator can readily be used for this purpose. So, we import this
    class and create an instance of the generator. We are using Keras to retrieve images from the disk with
    the flow_from_directory method of the ImageDataGenerator class.

    Convolution
    Cat and dog classification using CNN
    Convolution is a linear operation involving the multiplication of weights with the input. The
    multiplication is performed between an array of input data and a 2D array of weights known
    as filter or kernel. The filter is always smaller than input data and the dot product is
    performed between input and filter array.

    Activation

    The activation function is added to help ANN learn complex patterns in the data. The main
    need for activation function is to add non-linearity into the neural network.

    Pooling

    The pooling operation provides spatial variance making the system capable of recognizing an
    object with some varied appearance. It involves adding a 2Dfilter over each channel of the
    feature map and thus summarise features lying in that region covered by the filter.

    So, pooling basically helps reduce the number of parameters and computations present in the
    network. It progressively reduces the spatial size of the network and thus controls overfitting.
    There are two types of operations in this layer: Average pooling and Maximum pooling.
    Here, we are using max pooling which according to its name will only take out the maximum
    from a pool. This is possible with the help of filters sliding through the input and at each
    stride, the maximum parameter will be taken out and the rest will be dropped.

    The pooling layer does not modify the depth of the network unlike in the convolution layer.

    Fully Connected
    Cat and dog classification using CNN
    The output from the final Pooling layer which is flattened is the input of the fully connected layer.

    The Full Connection process practically works as follows:

    The neurons present in the fully connected layer detect a certain feature and preserves its value
    then communicates the value to both the dog and cat classes who then check out the feature and
    decide if the feature is relevant to them.

    We are fitting our model to the training set. It will take some time for this to finish.
    Cat and dog classification using CNN

    It is seen that we have 0.9750 accuracies on our training set.


    We can predict new images with our model by predict_image function where we have to
    provide a path of new image as image path and using predict method. If the probability is
    more than 0.5 then the image will be of a dog else of cat.
    Cat and dog classification using CNN

    Features Provided:

    We can test our own images and verify the accuracy of the model.

    We can integrate the code directly into our other project.

    We can extend the project to different entities by just finding the suitable dataset, change the
    dataset and train the model accordingly.

    You might also like