Mask Detector with FastAI and Streamlit Sharing. I want to use this post to highlight how easy it was to deploy an accurate Deep Learning Web Application. FastAI recommends using Binder, but I found this to be very slow compared to Streamlit.
Text Classification is a notorious problem in the field of NLP. However, the dawn of the ‘NLP evolution’ in recent years has made it easy to tackle such a problem without needing an expertise in the field. Recent advancements have helped us realize that models can act as better classifiers if they understand the language first(language modelling).
We’ll start with a discussion of Bayes’ Theorem, then we’ll use it to derive the Naive Bayes Classifier. Next, we’ll apply the Naive Bayes classifier to our movie reviews problem. Finally, we’ll review the prescription for building a Naive Bayes Classifier.
ML Environment jumpstart kit — robust, scalable, functional, load balanced, asynchronous, containerized, ready to deploy — for enterprise.Enterprise Scale ML Jumpstart Kit — FastAI + RabbitMQ + Docker. ML Environment jumpstart kit — robust, scalable, functional, load balanced, ...
Why I use Fastai and you should too. This is part 1 of a multipart series: The things I love the most about my favorite deep learning library, fastai.
In this article, I’m going to explain my experiments with the Kaggle dataset “Chest X-ray Images (Pneumonia)” and how I tackled different problems in this journey which led to getting the perfect accuracy on the validation set and test sets.
How to implement augmentations for Multispectral Satellite Images Segmentation using Fastai-v2 and Albumentations. Improve the performance of your deep learning algorithms with multispectral image augmentations and Fastai v2
Create your own cat/dog classifier in no time! This post will be the first part in a series where I introduce basic concepts of Deep Learning (DL), based on the fast.ai course.
In this article, I’ll be illustrating how to approach a core computer vision problem known as semantic segmentation. Simply put, semantic segmentation’s goal is to simply classify each pixel in a given image to a particular class according to what is shown in the image.
Deep Learning With Weighted Cross Entropy Loss On Imbalanced Tabular Data Using FastAI. A guide to building deep learning models easily while avoiding pitfalls
Fastai - Disaster Prediction using ULMFiT. Transfer Learning’s application in the field of Natural Language Processing
Build any deep-learning image classifier under 15 lines of code using fastai v2. This article was written with total beginners in mind, and you would be able to follow it even if you have little coding experience.
This post goes through the process of making a text classifier which takes in a piece of text (phrase, sentence, paragraph any length text) and tells if the text falls under a range of different types of malignant prose.
In this article I want to expand on what in my opinion is needed for an accessible applied deep learning platform. In addition, I want to go into the relation between more fundamental research and applied deep learning.
Datablocks API & Image Classification in fastai using Lego Minifigures Dataset. I can do this all day — Steve Rogers
In this post we will show you how to crack CAPTCHA using ResNet-50 without using OCR. After completing Jeremy Howard’s excellent deep learning course , I was wondering if I could crack real world CAPTCHAs by basic neural nets instead of using the conventional OCR technique.
Metastatic Adenocarcinoma Classification Using Convolutional Neural Networks. In this post, I used two different machine learning libraries (fastai and Keras) to solve the origin of metastatic adenocarcinoma.
Today, we’ll be discussing two of them. We’ll be using fastai2 which is a library built by Sylvain Gugger and Jeremy Howard which is an awesome interface built on top of PyTorch for performing deep learning experiments.
Fast.ai makes it easy to migrate from PyTorch, Ignite, or any other PyTorch-based library, or use fastai in conjunction with other libraries.
Fast.ai makes it easy to migrate from PyTorch, Ignite, or any other PyTorch-based library, or use fastai in conjunction with other libraries. On Friday, Jeremy Howard’s fast.ai announced the release of super productive libraries along with a very handy machine learning book and also a course. Fast.ai is popular deep learning that provides high-level components to obtain state-of-the-art results in standard deep learning domains.