Fastai2 Blog Posts, Projects, and Tutorials

Hi guys,

I’m experimenting with transfering Pytorch/Keras/TF models to Fastai. My last post was about molecule generation using LSTM. Today I bring you a Message Passing Neural Net for bioactivity prediction!

The model architeture comes from this paper: https://jcheminf.biomedcentral.com/articles/10.1186/s13321-019-0407-y

And you can find the original implementation here: https://github.com/edvardlindelof/graph-neural-networks-for-drug-discovery

For those of you looking for new, cool models to use for drug discovery studies using fastai, here’s my notebook showing the working model:

8 Likes

File not found, for the link shared.

just edited

Hey guys!
I started a little project where I created a web app with binder to predict my ratings for a book given the text of an uploaded image.

I didn’t get the example of Jeremy working (voila_bears) so if anyone of you tries to make Binder work, check out my repo: https://github.com/lschmiddey/book_recommender_voila

My blogposts to this project can be found here: https://lschmiddey.github.io/fastpages_/2020/09/28/Build-binder-app-Part4.html

I hope you enjoy it!

Lasse

2 Likes

Hi all,

I just published a two-part introductory article on building your own image classifier for deep learning beginners - if you’ve already completed Lessons 1-3 this is nothing new, but my target audience is myself before I started Deep Learning 2 years ago.

Its a hands-on article so it walks you through building a dataset and a model on Colab and running it on binder. If you have problems in the walk-through, I’d appreciate a comment so I can fix it…

Here’s the link : https://medium.com/@butchland/build-and-run-your-own-image-classifier-using-colab-binder-github-and-google-drive-part-1-bd1aebc626e

Best regards,

4 Likes

btw, forgot to mention :grinning: thanks to @joedockrill for the jmd_imagescraper package and @vikbehal for the binder instructions – hope you get to see your contributions in the article!

Best regards,
Butch

2 Likes

Hi all, my name is Dino and I am new to fastai. I absolutely love the material and the teaching style. I’ve read the first 7 chapters in the book and listened to the lectures online. Before moving further into the book, I decided to jump into a project and I was able to create a multilabel classification model on the “chinese-mnist” dataset. I would appreciate any feedback and I am really excited about moving forward with this course.

https://www.kaggle.com/dinodelao/fastai-v2-gpu-for-chinese-mnist-prediction

Hi All,

I have written a couple of blog posts explaining the workings of FastAI Optimizers and FastAI training loop. I have read the source code for these and have demonstrated my understanding with an Image classification example. Find the link to my posts below. Hopes this will be helpful.

  1. Study the resnet34 model architecture and build it using plain Python & PyTorch.
  2. Deep dive into FastAI optimizers & implement a NAdam optimizer.
  3. Study FastAI Learner and Callbacks & implement a learning rate finder (lr_find method) with callbacks.

Regards
Rakesh Sukumar

3 Likes

I’ve written my blog around the stacking of tensors using PyTorch.

For e.g. I’ve used MNIST dataset. This is my first blog in deep learning. So, please give it a read and let me know if any changes need to be made.

Thank you :slight_smile:

2 Likes

Just added my first blog on image classification using fast.ai’s vision library and jmd_imagescraper !! Please feel free to critique it.
You can find it at: A Beginner’s guide to Deep Learning

2 Likes

New blog post:

Check it out and please let me know if you find the visualizations helpful, or what can be improved :slight_smile:

6 Likes

My first blog.
Wrote a blog post for beginner like me who struggle with voila and heroku.


Please let me know if there’s any problem :smile:
1 Like

Hi karynaur Great post with informative and fun references.

Cheers mrfabuluous1 :smiley: :smiley:

1 Like

Hey there, recently I wrote my first blog post on deep learning. In this post I investigated how a batch size affects learning when we train image classifiers on natural images: https://nikita.melkozerov.dev/posts/2021/01/transfer-learning-and-resnet-in-search-of-a-perfect-batch-size/

6 Likes

Hi Nikita Melkozerov Hope you are having an excellent day.

Great enjoyable and clear post with some interesting results.

Thanks mrfabulous1 :smiley: :smiley:

1 Like

I continued to reflect my new knowledge in blog posts, so there is a new post about classifying digits from MNIST dataset from scratch. It was inspired by the chapter 4 of the fastbook, except this time we classify all 10 digits, and have some fun with different loss functions.

1 Like

MNIST Handwritten digits classification from scratch using Python Numpy - A beginner friendly blog on writing a deep learning model to classify MNIST in vanilla python :slight_smile:

2 Likes

Hi karynaur hope all is well!
I found your post very enjoyable and informative.
:clap: :clap: here’s a couple of claps as I am not on https://towardsdatascience.com/

Cheers mrfabulous1 :smiley: :smiley:

1 Like

Thank you @mrfabulous1 for taking the time to read it!! :slight_smile: :slight_smile:

Hello friends! :grinning:

I recently started working through the fastbook, and created two posts covering chapters 4 and 5. Use the posts to supplement the videos, and please feel free to reach out if you have any feedback!