Rate Severity of Toxic Comments using RoBERTa in PyTorch Lightning
The 4th Kaggle competition by Google’s Jigsaw group aims at predicting more or less toxicity between a pair of comments. This code walkthrough blog builds an initial pipeline in Pytorch Lightning. It touches important topics like cosine annealing, mixed precision and uses RoBERTa Model for training etc.
This Kaggle competition aims at finding out popularity of the shelter pets to speed up their adoption process. This post explains problem statement, plays with evaluation matric rmse and provide some key techniques that can be used for strong finish on kaggle leaderboard. We have even Provided sample code to give you a headstart.
How to begin with Chaii — Hindi, and Tamil Question Answering competition
Explore how to start with the Kaggle competition chaii - Hindi and Tamil Question Answering. Blog explains problem statement, plays with evaluation matric and provide ssome key techniques that can be used for strong finish on kaggle leaderboard.
Understanding and Building Resnets from scratch using Pytorch
Resnets are the go-to architecture for most of the deep learning tasks. What makes them so popular? Resnets introduced residual blocks which made deeper neural networks possible. In this post, Poonam Ligade shares understanding of resnets and shows how you can build Resnet from scratch using Pytorch.
Identifying people without Masks - Using Deep Learning/AI
Vishnu Subramanian takes you through high level steps required for building an object detection pipeline for identifying persons without masks. He also discusses the challenges faced with this approach. Along with that he shares how we can use deep learning algorithms to help us in semi-automating the labelling task.
Building image segmentation algorithm using fastai2/PyTorch Part - 1
The first post in series introduces the problem of identifying salt deposits beneath the earth, describes why we choose fastai2 and build a data pipeline required for training a segmentation algorithm.
Building image segmentation algorithm using fastai2/PyTorch Part - 2
Learn about how to build a unet model for image segmentation with a custom encoder. Along the way you will build a solution which ranks in the top 4% of kaggle leaderboards. We will also create a pipeline required for predicting the test data, applying custom TTA and generating a kaggle submission file.
Understanding Autoencoders and Variational Autoencoders
In the recent years, computer vision algorithms have achieved many things. One amazing and dangerous thing they can do is generate new images, faces, voices, etc. Let's look at the fundamental techniques that power modern generative, segmentation models and much more.
7 Tips and tricks for transfer learning in Pytorch
Transfer learning has become a key component of modern deep learning, both in the fields of CV and NLP. Read the post to learn how to tweak your neural network to achieve better results from your data.