Explored @huggingface spaces today. It's freaking awesome 🤯
Definitely using it in my current project with HF.
A thread about its awesome offerings and features 🧵
1. You can deploy your Streamlit or Gradio apps in a matter of a few clicks 🚀
Oct 21, 2021 • 25 tweets • 7 min read
Memory Efficient Coding in #PyTorch ⚡
20 tricks to optimize your PyTorch code
Let's break some of the bad habits while writing PyTorch code 👇
A thread 🧵
1. PyTorch dataloader supports asynchronous data loading in a separate worker subprocess. Set pin_memory=True to instruct the DataLoader to use pinned memory which enables faster and asynchronous memory copy from host to GPU
Sep 18, 2021 • 11 tweets • 2 min read
So, recently there was this question from @svpino that in theory, you can model any function using a neural network with a single hidden layer. However, deep networks are much more efficient than shallow ones. Why?
Here's a thread answering that question🧵
📌 Both shallow (network with one hidden layer) and deep networks(network with multiple hidden layers) are capable of approximating any function (theoretically). But, still, you get better results with deep neural networks. Here's why 👇
Sep 10, 2021 • 13 tweets • 2 min read
I am using @weights_biases from past 4-5 months and I am in love with the product. It makes working with Deep Learning projects super easy, trackable and fun. Here are some of my favourite features of wandb 👇
1. It is super easy to integrate Weights and Biases with any framework of your choice
Aug 15, 2021 • 14 tweets • 6 min read
Some of the best resources I came across for intuitively visualizing #NeuralNetworks (how they transform data and classify stuff).
With these resources, Neural Networks will be no longer black boxes for you'll.
A thread 🧵
A playlist by none other than @3blue1brown explaining how forward and backward propagation works with great visualizations as always. You can't miss this ... youtube.com/playlist?list=…
Aug 14, 2021 • 9 tweets • 2 min read
What is sampling in #MachineLearning and what are different sampling techniques?
Detailed analysis of 10 widely used sampling techniques. (Notes at the end 👇)
A thread 🧵
PS: There is a Notion document at the end of the thread with detailed notes on this topic 😎
Population vs Sample ✨
📌 Population - Population is the collection of the elements which has some or the other characteristic in common.
📌 Sample - Sample is the subset of the population. The process of selecting a sample is known as sampling
Aug 9, 2021 • 9 tweets • 2 min read
How to learn a Machine Learning algorithm?
Everything you need to consider while approaching to learn a #MachineLearning algorithm 👇
A thread 🧵
1. Get the intuition behind the algorithm (i.e its core ideas and why the algorithm is there in the first place).
--- 2. Get the mathematical intuition behind the algorithm (understand the math working under the hood).
---
