Skip to content

Commit

Permalink
Image Classifivation with TensorFLow/Keras (#501)
Browse files Browse the repository at this point in the history 
* images for webscraping blog

Images that are use in Web Scraping blog.

* Banner Image for WebScraping

This is the banner image that you asked for to use on the blog. So here, I changed it for Web Scraping Introduction Blog.

* image for chatbot content

* flowchart image to build a chatbot with NLTK

* Images of ChatBot with NLTK article

* Image Classification with TensorFLow/Keras.

* Image_Classification article's image

* Image for ImageClassificationwithTensorFLow/Keras.
  • Loading branch information
@vaishali-sharma-20
vaishali-sharma-20 authored Jul 3, 2024
1 parent 2c39277 commit 0131de6
Show file tree
Hide file tree
Showing 2 changed files with 307 additions and 0 deletions.
307 changes: 307 additions & 0 deletions posts/Image Classification/ImageClassificationWithTensorFLow.html
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,307 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta
name="viewport"
content="width=device-width, initial-scale=1, shrink-to-fit=no" />
<meta
name="description"
content="A deep learning model to classify images using TensorFlow and Keras. Use a pre-trained model or build your own convolutional neural network (CNN)." />
<meta
name="keywords"
content="Image Classification, TensorFlow, Keras, Deep Learning, Convolutional Neural Networks (CNN), Data Augmentation, Transfer Learning, Model Evaluation, Pre-trained Models, On-device Machine Learning" />
<title>
Image Classification with TensorFlow/Keras
</title>
<meta name="vaishali-sharma" content="CSEdge" />
<!-- Favicon-->
<link
rel="icon"
type="image/x-icon"
href="https://csedge.courses/Images/CSEDGE-LOGO32X32.png" />
<!-- Core theme CSS (includes Bootstrap)-->
<link href="../styles.css" rel="stylesheet" />
</head>
<body>

<nav class="navbar navbar-expand-lg navbar-dark bg-dark">
<div class="container">
<img
height="32px"
width="32px"
src="https://csedge.courses/Images/CSEDGE-LOGO32X32.png"
alt="logo" />
<a class="navbar-brand" href="../.././index.html">CSEdge Learn</a>
<button
class="navbar-toggler"
type="button"
data-bs-toggle="collapse"
data-bs-target="#navbarSupportedContent"
aria-controls="navbarSupportedContent"
aria-expanded="false"
aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div class="collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav ms-auto mb-2 mb-lg-0">
<li class="nav-item">
<a class="nav-link" href="https://learn.csedge.courses">Home</a>
</li>
<li class="nav-item">
<a class="nav-link" href="https://csedge.courses/about">About</a>
</li>
<li class="nav-item">
<a class="nav-link" href="https://csedge.courses#contact"
>Contact</a
>
</li>
<li class="nav-item">
<a
class="nav-link active"
aria-current="page"
href="https://learn.csedge.courses">Blog</a>
</li>
</ul>
</div>
</div>
</nav>
<div class="container mb-4 mt-4">
<div class="row">
<!-- Blog entries-->
<div class="col-lg-8">
<h1>
Image Classification with TensorFlow/Keras
</h1>
<!-- Featured blog post-->
<div class="card mb-4">
<img
class="card-img-top"
src="../images/Image_Classification.png"
alt="Image Classification with TensorFlow" />
<div class="card-body">
<main class="container">
<section>
<p>Image classification is a fundamental task in computer vision, where the goal is to assign a label (class) to an input image. In this tutorial, we’ll explore how to build an image classification model using TensorFlow and Keras. You can either use a pre-trained model or create your own custom convolutional neural network (CNN).</p>
<br>
<h2>Pre-requisites</h2>
<p>Before we dive into the implementation, make sure you have the following installed:</p>
<ul>
<li>Python (preferably Python 3.6 or later)</li>
<li>TensorFlow (install using pip install tensorflow)</li>
<li>Keras (included with TensorFlow)</li>
</ul>
<h2>Workflow Overview</h2>
<ol>
<h6><li>Data Preparation</li></h6>
<ul>
<li>Collect a labeled dataset of images. For example, you can use the <a href="https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz">Flower Photos dataset</a>.</li>
<li>Organize the data into subdirectories, each representing a different class (e.g., roses, tulips, dandelions).</li>
</ul>
<h6><li>Load and Preprocess Data:</li></h6>
<ul>
<li>Use <code>tf.keras.utils.image_dataset_from_directory</code> to efficiently load images from disk.</li>
<li>Resize images to a consistent size (e.g., 180x180 pixels).</li>
<li>Normalize pixel values to the range [0, 1].</li>
</ul>
<h6><li>Model Building:</li></h6>
<ul>
<li>Choose between using a pre-trained model (transfer learning) or building your own CNN from scratch.</li>
<li>For transfer learning, load a pre-trained model (e.g., MobileNetV2, ResNet50) and fine-tune it for your specific task.</li>
<li>For custom CNN, design your architecture with convolutional layers, pooling layers, and fully connected layers.</li>
</ul>
<h6><li>Compile and Train the Model:</li></h6>
<ul>
<li>Compile the model with an appropriate optimizer, loss function, and evaluation metric.</li>
<li>Train the model on your labeled dataset.</li>
<li>Monitor training progress and adjust hyperparameters as needed.</li>
</ul>
<h6><li>Evaluate and Improve:</li></h6>
<ul>
<li>Evaluate the model’s performance on a validation set.</li>
<li>Address overfitting by using techniques like data augmentation and dropout.</li>
<li>Fine-tune the model based on evaluation results.</li>
</ul>
<h6><li>Prediction and Deployment:</li></h6>
<ul>
<li>Use the trained model to predict labels for new images.</li>
<li>Convert the model to TensorFlow Lite format for deployment on mobile devices or embedded systems.</li>
</ul>
</ol>
<h2>Example Code</h2>
<p>Below is a simplified example of building an image classification model using a custom CNN:</p>
<strong>Python:</strong><br>
<pre>
<code>
import tensorflow as tf
from tensorflow.keras import layers

# Load and preprocess data
data_dir = "/path/to/flower_photos"
batch_size = 32
img_height, img_width = 180, 180

train_ds = tf.keras.utils.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="training",
seed=42,
image_size=(img_height, img_width),
batch_size=batch_size,
)

# Build a simple CNN
model = tf.keras.Sequential([
layers.Conv2D(32, (3, 3), activation="relu", input_shape=(img_height, img_width, 3)),
layers.MaxPooling2D(),
layers.Flatten(),
layers.Dense(128, activation="relu"),
layers.Dense(num_classes, activation="softmax"), # num_classes = number of flower classes
])

# Compile the model
model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"])

# Train the model
model.fit(train_ds, epochs=10)

# Evaluate the model (on validation set)
validation_ds = tf.keras.utils.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=42,
image_size=(img_height, img_width),
batch_size=batch_size,
)
model.evaluate(validation_ds)

</code>
</pre>

<p>Remember to replace <code>/path/to/flower_photos</code> with the actual path to your dataset directory.</p>
<h2>Conclusion</h2>
<p>Image classification with TensorFlow and Keras is a powerful technique that can be applied to various domains, from recognizing objects in photos to medical diagnosis. Experiment with different architectures, hyperparameters, and datasets to improve your model’s accuracy!</p>
</section>
</main>
</div>
</div>
</div>
<!-- Side widgets-->
<div class="col-lg-4">
<!-- Search widget-->
<div class="card mb-4">
<div class="card-header">Search</div>
<div class="card-body">
<div class="input-group">
<input
class="form-control"
type="text"
id="searchInput"
placeholder="Enter search term..."
aria-label="Enter search term..."
aria-describedby="button-search" />
<button
class="btn btn-primary"
id="button-search"
type="button"
onclick="search()">
Go!
</button>
</div>
</div>
<!-- Search Results -->
<div id="searchResults"></div>
</div>
<!-- Categories widget-->
<div class="card mb-4">
<div class="card-header">Categories</div>
<div class="card-body">
<div class="row">
<div class="col-sm-6">
<ul class="list-unstyled mb-0">
<li><a href="#!">Web Design</a></li>
<li><a href="#!">HTML</a></li>
<li><a href="#!">Freebies</a></li>
</ul>
</div>
<div class="col-sm-6">
<ul class="list-unstyled mb-0">
<li><a href="#!">JavaScript</a></li>
<li><a href="#!">CSS</a></li>
<li><a href="#!">Tutorials</a></li>
</ul>
</div>
</div>
</div>
</div>
<!-- Side widget-->
<div class="card mb-4">
<div class="card-header">Recent Posts</div>
<div class="card-body">
<p>Coming Soon..!</p>
</div>
</div>
<div class="card mb-4">
<div class="card-body">
<script
async
src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js?client=ca-pub-8930077947690409"
crossorigin="anonymous"></script>
<ins
class="adsbygoogle"
style="display: block"
data-ad-format="fluid"
data-ad-layout-key="-fb+5w+4e-db+86"
data-ad-client="ca-pub-8930077947690409"
data-ad-slot="9866674087"></ins>
<script>
(adsbygoogle = window.adsbygoogle || []).push({});
</script>
<script
async
src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js?client=ca-pub-8930077947690409"
crossorigin="anonymous"></script>
<ins
class="adsbygoogle"
style="display: block"
data-ad-format="fluid"
data-ad-layout-key="-fb+5w+4e-db+86"
data-ad-client="ca-pub-8930077947690409"
data-ad-slot="9866674087"></ins>
<script>
(adsbygoogle = window.adsbygoogle || []).push({});
</script>
<script
async
src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js?client=ca-pub-8930077947690409"
crossorigin="anonymous"></script>
<ins
class="adsbygoogle"
style="display: block"
data-ad-format="fluid"
data-ad-layout-key="-fb+5w+4e-db+86"
data-ad-client="ca-pub-8930077947690409"
data-ad-slot="9866674087"></ins>
<script>
(adsbygoogle = window.adsbygoogle || []).push({});
</script>
</div>
</div>
</div>
</div>
</div>
<!-- Footer-->
<footer class="py-5 bg-dark">
<div class="container">
<p class="m-0 text-center text-white">
Copyright &copy CSEdge Learn 2024
</p>
</div>
</footer>
<!-- Bootstrap core JS-->
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/bootstrap.bundle.min.js"></script>
<!-- Core theme JS-->
<script src="../script.js"></script>
</body>
</html>
Binary file added posts/images/Image_Classification.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 0131de6

Please sign in to comment.