Welcome to this project on Image Classification with Pre-trained InceptionV3 Network. This project aims to impart the knowledge of how to access the pre-trained models(here we get pre-trained Inception model) from Keras of TensorFlow 2, and appreciate its powerful classification capacity by making the model predict the class of an input image.
Understanding the pre-trained models is very important because this forms the basis of transfer learning. one of the most appreciated techniques to perform the classification of a different task thus reducing the training time, the number of iterations, and resource consumption. Learning about the pre-trained models and …
Welcome to this project on Building a CNN Classifier using TensorFlow 2 for MNIST Fashion Dataset. In this project, we will understand how to use the TensorFlow 2 platform to build a simple classifier using Convolutional Neural Networks(CNNs).
CNNs have been one of the state-of-art tools in the current era of Computer Vision. The present-day deep learning and computer vision communities find numerous applications of CNNs in classification tasks and object detection use cases. These use cases have formed the basis of many real-time applications like self-driving cars, face recognition apps, satellite photo analysis and classification, and many more …
Welcome to this project on NYSE Closing Price Prediction. In this project, you will use Pandas, Keras, and Python in order to build a predictive model and apply it to predict the closing prices.
Time-series modeling has a huge demand in today's numbers-filled world. It has a wide variety of applications in sales s forecasting, prediction of meteorological elements like rainfall, economic forecasting in the financial worlds, and many more.
In this exercise, we shall understand how to predict stock market closing prices for a firm using GRU, a state-of-art deep learning algorithm for sequential data. We shall focus …
Welcome to the project on Building a Neural Network for Image Classification with TensorFlow. In this project, we would learn how to develop a neural network classifier from very scratch, using TensorFlow 2.
We would build and train a dense neural network on the Fashion MNIST dataset and evaluate its performance with some test samples. This project aims to impart the knowledge of the basic steps involved in building a neural network, working with TensorFlow 2, training a neural network, and make the learner comfortable with the cutting-edge technology - TensorFlow 2.
Skills you will develop:
Welcome to this project on Image Classification with Pre-trained Keras models. This project aims to impart the knowledge of how to access the pre-trained models(here we get pre-trained ResNet model) from Keras of TensorFlow 2, and appreciate its powerful classification capacity by making the model predict the class of an input image.
Understanding the pre-trained models is very important because this forms the basis of transfer learning. one of the most appreciated techniques to perform the classification of a different task thus reducing the training time, the number of iterations, and resource consumption. Learning about the pre-trained models and …
Welcome to the project on Training from Scratch vs Transfer Learning. In this exercise, we will understand how to train a neural network from scratch to classify data using TensorFlow 2. We would also learn how to use the weights of an already trained model to achieve classification to another set of data.
We will train a neural network (say model A) on data related to 6 of the classes, and we will train another neural network (say model B) on the remaining 2 classes. Then, we would use the pre-trained weights of model A and tune the last layer …
Welcome to the project on Mask R-CNN with OpenCV for Object Detection. In this project, we will learn how to read a pre-trained TensorFlow model for object detection using OpenCV.
The real-world scenarios have a lot of applications based on object detection. For example, object detection models are used in self-driving cars to recognize where the pedestrians are, where the are vehicles located, where the signals are, etc in the given frame of view. So, it is very important to develop an understanding of how to use a pre-trained object detection model so that we could later customize it based …
Welcome to this project on the Neural Style Transfer. In this project, you will use TensorFlow 2 to generate an image that is an artistic blend of a content image and style image.
Neural Artistic Style Transfer finds a wide range of applications to fancily modify images. This field has so much influenced the technical world that many apps, such as Prisma, have received great craze amongst the users. In recent days, decent work has also been done in this area, which served as a holy grail to our project. The heart of this capability is the convolutional neural network …
Welcome to this project on Sentiment Analysis using TensorFlow 2. This project aims to impart an understanding of how to process English sentences, apply NLP techniques, make the deep learning model understand the context of the sentence, and classify the sentiment the sentence implies.
Our real-world is being flooded with a lot of reviews all around us. Be it an online shopping mart, movie reviews, offline market, or anything else. It has become very common for us to rely on these reviews. Hence it would be really helpful for a Machine Learning aspirant to understand various techniques related to processing …
Welcome to this project on Cat vs Non-cat Classifier using Transfer Learning. In this project, you will use Python and Keras to apply the Transfer Learning technique in order to build an image classifier, and apply it to predict the class of an input image - whether it is a cat or a non-cat.
Deep Learning is computationally intensive, often demanding powerful computational resources to yield reasonable accuracies in the real world. The idea of Transfer Learning has become a boon for the computer vision and deep learning community as it has reduced the hunger of Deep Learning algorithms for powerful …
Welcome to the project on Working with Custom Loss Function. This project aims to provide an understanding of how we could use the custom defined loss functions along with TensorFlow 2.
Though TensorFlow 2 already provides us with a variety of loss functions, knowing how to use a user-defined loss function would be crucial for a machine learning aspirant because often times in real-world industries, it is expected to experiment with various custom defined functions. This exercise is designed to achieve that goal.
Skills you will develop:
Welcome to this project on Classifying Flowers in Iris dataset with Deep Neural Network using Keras. In this project, you will use Python and Keras to build a Deep Neural Network, and apply it to predict the classes of Flowers in the Iris dataset.
Keras is one of the most extensively used APIs in the world of Deep Learning. It provides an amazing developer-friendly deep learning framework to build deep learning models with wide-ranging features to support high scalability, because of which it is not only widely used in academics but also in organizations to build state-of-the-art research models. In …
Welcome to this project on Autoencoders for MNIST Fashion. In this project, we will understand how to implement Autoencoders using TensorFlow 2.
We will be understanding how to practically implement the autoencoder, stacking an encoder and decoder using TensorFlow 2. We will also depict the reconstructed output images by the autoencoder model.
Skills you will develop:
TensorFlow 2
scikit-learn
Matplotlib
Numpy
Welcome to the project on Hosting an Image Classification App on Heroku. In this project, we will get a basic understanding of how to deploy a web app on Heroku, a Platform as a Service.
Heroku is a cloud platform for the deployment and management purposes of web applications. It could be considered as one of the best solutions for hosting web-apps very quickly, thus allowing the developer to concentrate more on development.
Welcome to the project on How to build low-latency deep-learning-based flask app. In this project, we will refactor the entire codebase of the project [ How to Deploy an Image Classification Model using Flask][1]. That monolithic code will be refactored to form two microservices - the flask service and model service. The model service acts as a server that renders pretrained Tensorflow model as a deep learning API, and keeps listening for any incoming requests. The flask service requests the model service, and displays the response from the model server. This way, we write cleaner code and promote service isolation.
Further …