Share your work here ✅

tawfik · August 18, 2020, 11:58am

Hi vlad,

Could you add any any instructions how to do it, I am using the some configuration as you but I can’t install the whole thing.

best

apsal · August 19, 2020, 12:52pm

Just built my version of the face-mask detector after completing lesson 2, with streamlit.
mask-ornot.herokuapp.com
and here’s the repo.
Found all the help needed here in this forum.

UKamath7 · August 22, 2020, 4:02pm

Another perspective of learning fastai course

Nubbinsonfire · August 22, 2020, 4:36pm

I have been trying to do binary segmentation, for hair from peoples faces, and think its been doing quite well at the moment. I even combined it with a color LUT to do some nice recoloring of hair. !

joedockrill · August 22, 2020, 5:15pm

@muellerzr this thread should be moved to 2020 i assume?

muellerzr · August 22, 2020, 5:17pm

2020 has it’s own

sachinruk · August 25, 2020, 12:22pm

Survival Analysis with pytorch using nbdev. At the end of the day it’s just another loss function. Made the docs so that (hopefully) you can understand the theory as well as code.

Still some work to be done in the Accelerated Failure Time models, but here’s the alpha: https://sachinruk.github.io/torchlife/

SravanVoonna · August 29, 2020, 12:46pm

I used UNET architecture for generators in Cycle GAN. I observed a significant improvement.

Here is my work

dipam7 · September 3, 2020, 12:04am

I wrote a quick article on how to use Streamlit to quickly test your models. This can be used for fastai models as well. Link below

https://towardsdatascience.com/streamlit-use-data-apps-to-better-test-your-model-4a14dad235f5

mrfabulous1 · September 3, 2020, 6:35am

Hi dipam7 hope all is well!
Great short post"
not registered with medium_com
Cheers mrfabulous1

rajirai · October 14, 2020, 2:04pm

Hi,

I have written a blog and developed a Covid19 chest X-ray image classifier based on the initial 3 lessons. Here are the links:

github.com

RajiRai/FastAI/blob/master/Covid19_prediction_using_X_ray.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Covid19 prediction using X-ray",
      "provenance": [],
      "authorship_tag": "ABX9TyPiWbUmj+ER8bEWYjvcuX1n",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "c74c4e3ef13744b7b0c731988c2abd08": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "VBoxModel",

This file has been truncated. show original

https://www.kaggle.com/krrai77/fast-ai-lesson-3-covid19-x-ray-classifier-app

Thanks
Raji

nofreewill · November 30, 2020, 8:17pm

I’ve figured out that we don’t have to do any fine-tuning but just correct the weights in the bigger kernel with respect to how much bigger it got.
5x5->9x9; have to multiply the weights by (5x5)/(9x9).

Daguer · November 30, 2020, 8:50pm

Nice mind map ! I like it

elena_khachatryan · January 20, 2021, 2:12pm

Hi everyone! Want to introduce the Weights & Biases report about transformers, which dives into the breakthroughs, scientific basis, formulas, and code for the transformer architecture, which you can read in the Chinese.
Report: https://lnkd.in/eVi74B9

marcossantana · February 3, 2021, 1:32am

Our paper using ULMFit to generate potential inhibitors of SARS-CoV-2 Mpro is finally here!

AnkurBassi · March 21, 2021, 9:02am

Recognising MNIST digits using mean of pixel values, without any machine learning algorithm

I have created a well documented python code for classifying digits without machine learning. Will be happy to hear the suggestions for improving the code.

I can reached at: ankbassi100@gmail.com

AGSL · April 23, 2021, 7:16pm

How to Deploy Fast.ai Models? (Voilà , Binder and Heroku)

Medium article:

code:

I hope this may help.

AGSL · April 25, 2021, 3:40pm

Car Type Classification

Classifies 4 types of cars.

Convertible
Pickup
Sedan
Station Wagon

https://medium.com/unpackai/creating-a-fastai-car-type-classification-model-using-a-custom-dataset-653457b26056

dipam7 · May 12, 2021, 7:02pm

In this article, I use a fun little example of how pytorch-lightning started to demonstrate the power of GitHub Actions

https://dipam44.medium.com/the-simplest-introduction-github-actions-43e86b05317

idraja · May 23, 2021, 10:41pm

I was a bit fuzzy about python decorators, and since they’re used everywhere in fastai I decided to dig in and wrote this post, which is part 1 of 2 parts.

The next post is going to be about dissecting the fastai function module which had me confused for quite a bit before I started to break it down!

feedback welcome.