Ishan Dutta Profile picture
Jan 20, 2022 13 tweets 9 min read Read on X
I have written 1000s of lines of code and built multiple projects in PyTorch.

On @PyTorch 's 5 year completion, I am sharing Top 10 resources you can use to learn this awesome Deep Learning framework from scratch!

A Visual Thread (with links)🧵👇
1️⃣ PyTorch Official Tutorials -

PyTorch has some extensive and clear tutorials in all domains like Text, Audio, Image, Video, Reinforcement Learning and so on.

Link👉bit.ly/3IswPPX PyTorch Official Tutorials
2️⃣ Deep Learning with PyTorch: Zero to GANs

Taught by @aakashns,

this @YouTube playlist teaches you creating a Linear Regression model in PyTorch all the way to creating a GAN to generate anime faces!

Link👉bit.ly/3fF6WzR Deep Learning with PyTorch: Zero to GANs
3️⃣ PyTorch Tutorials - Complete Beginner Course:

In this exhaustive @YouTube playlist, @python_engineer takes you through

basics of tensors, gradients,

models like Logistic Regression/RNN/GRU and

introduces PyTorch Lightning as well.

Link👉bit.ly/33Sa6O2
4️⃣ PyTorch Tutorials

This paylist is for people who love Deep Learning Research.

@aladdinpersson starts from the basics,

then moves through architecture by architecture in order of complexity

and provides basic paper explanations as well!

Link👉bit.ly/3IqPzzh PyTorch Tutorials
5️⃣ pytorch-tutorial:

A beautifully structured @github repository by @yunjey_choi

He has divided the tutorials in 4 sections -

Beginner, Intermediate, Advanced & Utilities.

It is recommended after completing the official PyTorch Tutorial.

Link👉bit.ly/3GLF6xD pytorch-tutorials
6️⃣ Dive into Deep Learning:

This is an interactive deep learning book with code, math, and discussions.

The code is available in NumPy/MXNet, PyTorch, and TensorFlow.

It is recommended to start after having prior experience with PyTorch.

Link👉bit.ly/3ryZfAS Dive into Deep Learning
7️⃣ Deep Learning for Coders with fastai and PyTorch:

A legendary book on @PyTorch and @fastdotai by @jeremyphoward and @GuggerSylvain

It dives progressively into deep learning theory and

you gain a complete understanding of the algorithms

Link👉bit.ly/3tGocNq Deep Learning for Coders with fastai and PyTorch
8️⃣ Natural Language Processing with PyTorch:

This book provides you with a solid grounding in NLP and Deep Learning

It demonstrate how to use PyTorch to build applications involving rich representations of text specific to the problems you face.

Link👉bit.ly/3FJoLbB Natural Language Processing with PyTorch
9️⃣ Modern Computer Vision with PyTorch:

One book which will hold your hands and make you fall in love with Computer Vision.

50+ PyTorch real world Computer Vision projects, all in one place!

Link👉bit.ly/3Im577b Modern Computer Vision with PyTorch
🔟Deep Learning with PyTorch:

Written by PyTorch’s creator and key contributors this book teaches you to develop deep learning models in a familiar Pythonic way.

Several PyTorch implementation based projects are available in this book.

Link👉bit.ly/3qImzgk Deep Learning with PyTorch
I share such insightful threads on a regular basis, follow @ishandutta0098 to stay updated.
If you enjoyed reading this thread, please retweet the first tweet so that more people can read this thread 👇

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Ishan Dutta

Ishan Dutta Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @ishandutta0098

Mar 10, 2022
Understanding how the dimension of your input image changes as it progresses through the Neural Network Layers can be challenging to understand at times.

There is a module named 'torchsummary' which can easily do this task for you!

Here is how it works.

A Visual Thread 🧵👇
1️⃣ Consider the above example where you have already defined a model named 'ConvNet', which has

- 2 convolutional layers,

- then a dropout

- and finally 2 linear layers.
2️⃣ Let us assume that you have a single channel image of size 28*28 which can be represented as (1, 28, 28).

Now, the task is to understand how the image dimesion changes with every layer.
Read 10 tweets
Mar 9, 2022
Just secured the 1st Position 🥇 in a @kaggle community competition hosted by @weights_biases and Deep Learning Sessions Portugal!

Know more 🧵👇
The challenge was a Multiclass Image Classification Problem consisting of 8 classes of Microscopic Blood cell images.
I trained 3 different models for this task which were -

1. EfficientNet-b0

2. EfficientNet-b1

3. SEResNext50
Read 8 tweets
Jan 19, 2022
I am excited to announce the registrations for Batch-7 of the Live Data Science Mentorship Session (January 2022)

400+ students across 5+ countries have taken the program & the response keeps me motivated to reach more people

Register Here - bit.ly/3FCWROp

Details 👇
There are 4 sections in the session -

1. A practical Data Science path which I followed

2. Secrets which helped me secure Top 30 ranks across multiple Machine Learning Hackathons (including Kaggle)
3. Mind blowing Tips & Tricks which will increase your chances by 60% to get shortlisted for off-campus opportunities

4. Live Q&A to clear all your doubts
Read 5 tweets
Dec 1, 2021
If you are willing to learn PyTorch and have understanding of some deep learning concepts

and hands on practice with python

then the best resource is the PyTorch Tutorials.
These Tutorials are available in the orginal PyTorch Website and are complete in a sense.
The best part is that it starts from as basic as how to declare a tensor

and takes you through various methods from Text, Image, Audio data and a lot more
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(