Share your work here ✅

Hi everyone: I created a model to identify edible vs poisonous mushrooms and I was surprised that it worked the first time. edible_vs_poisonous_mushrooms | Kaggle

It was fun but I didn’t really learn anything, just cut and paste the codes from lesson 1. Can someone suggest what I should do next and what I should focus on?

Thank you in advanced for your help.

I wanted to create a model that can identify the name of the composer from a music. But that’s long way out. For now, I wanted to revector the bird v. forest to identify the composers from various images downloaded from ddg.

I’d downloaded pictures of them with a nuance of ‘portrait’ and ‘group’ pictures. I thought this will download Mozart by himself and in a crowd. I didn’t think much that there were no cameras in Beethoven and Mozart’s era :slight_smile:

So, I was concerned to see the show_batch() included pictures of orchestra playing Mozart :frowning:

But thankfully, even with the glitch resnet18 did its job. It identified a sample picture of Beethoven with 99.8% accuracy.

Also, I fed it a mozart sample picture to see if there was a false positive. But this model with fine tuning predicted this as a mozart image with a 6/10 of 1% probability that it could be Beethoven.

You can check the notebook @ Beethoven or Mozart | Kaggle

Hi Everyone,

I just finished lesson 1 of the course, and thought I would share my simple yet tasty types of ramen classification model (miso, shio, shoyu, and tonkotsu). Just impressed with how easy fastai library makes it to download images, train, and test the model.


Please see below link to the classification model, which performs pretty well after just 3 epochs of fine tuning. Looking forward to learning and sharing more!

Ramen Classification Model


Hi all, I’m working on a tetris AI and would love feedback on how you think I could improve! Currently using vision_learner and fine tuning convnext_small_in22k.

Recorded Gameplay - 400k Training Samples

Kaggle Dataset

Kaggle Notebook

The dataset is pixel images translated from actual game frames and labeled with the next move made:

Current champion settings:


Trying Out document classification with Vision model

I’m excited to share my progress on the course! At my current organization, we were contemplating using Amazon Comprehend for a document classification use case. However, I decided to take a different approach and embarked on a project to build a document classifier using a vision model, although I’m still evaluating if this is the optimal strategy. Initially, I generated two styles of PDFs , converted those to images using a script generated from ChatGPT, and then fine-tuned a ResNet model using these document images. The resulting model is deployed on Hugging Face. My future plans for this project involve data extraction and storage in a database, and I’m considering creating templates for each PDF to facilitate data extraction. I’m open to any suggestions or insights from the community on how to further develop this project. I’d also like to express my gratitude to Jeremy for this incredible course, which has been truly inspiring. As of now, I’m progressing through the lessons on gradient boosting

Notebook Link : PDF classifier with vision models
PDF generator script: PDF generator and convert to images
Hugging Face Space URL: App

Looking for all your suggestions and feedback for improvements

1 Like

Hello, fastai community :). Excited to finally get started on this course.

For lesson 1 & 2 I made a recognizer of street art styles. In Paris :fr: where I live, there are many street artists active and often it’s hard to tell which piece of work was done by whom. The recognizer is trained on example works of 4 artists (50 samples from each).

Try it live, read more.

PS while at it, I also documented my pip-only no-conda setup on Mac with GPU acceleration in case it’s useful for others

1 Like

I created a waste or art classifier.

It classifies any image as one of five types of waste or fine art.

If you upload art and it gets classified as waste, please do not trash it. You are probably more talented than this model was trained to recognise.


Hello everyone,

this summer ib Berlin a huge police search was going on after a video went viral that supposedly showed a lioness at night. After some fearful days the authorities decided that is probably was a boar after all. I built an image classifier that might have spared them this wild goose chase. Find it here: BigCat Or Boar - a Hugging Face Space by ChrZeller

Hi everyone! I just started the course. For the first chapter, I built an image classifier to help categorize products into one of the main categories on my marketplace startup. Check it out on my blog if you want! Fast.AI Chapter 1. Recently, I’ve taken on the challenge… | by Jack Driscoll | Oct, 2023 | Medium

So excited to continue learning from the list course and do even more amazing things.

Inspired by “Is it a bird” kaggle notebook, I ran a similar experiment to use resnet34 to discern popular noodle dishes in my region (Singapore’s char kway teow vs Malaysia’s hokkien mee).

After five rounds of fine tuning, the error rate on the validation set was a surprisingly low 1.7% - even though the dataset was imperfect! Call me pleasantly surprised. Definitely looking forward to learn and experiment more with future lessons.

For anyone interested, this notebook can be found on Github.

1 Like

Thanks Jeremy for this wonderful course! I am beginning my journey with it. This is my first work - classifying buildings/structure design so that we can know if it is based on ancient or modern design.

Hi all, I built a toy classifier for Super Mario characters.

Hey everyone,
Just started the course this week and am blogging my progress and insights through the course here.

Since my account is new I can only add one link but my first three projects were:

  1. Broccoli or Weed
  2. Matt or Meth Damon] [Old breaking bad meme]
    3.Bridge type detector
1 Like

Have my second lesson basic project up with bears to keep things simple. Really neat!

Good morning everyone!
My friend and I recently wrote a book about practices in setting up RAG, based on our experience trying out LangChain, llamaindex, haystack etc.
I’d like to share it with ML/AI enthusiasts here.

Thank you everyone!


1 Like

Religious Celebration Detection

I trained about 600 images with resnet18, the computer vision model to determine if a celebration picture is Christmas, Easter, or Ramadan.

A sample of the result:

1 Like

This is great! I love how its using both gatherings and imagery related to the holidays.

1 Like

For week one I made a classifier for different types of bean lesions (sounds appetizing, right?) using one of the kaggle datasets.


I’m really happy that I’ve managed to deploy the model that I toyed with in week one in week 2. I retrained it and cleaned the data set, but it still was quite small. Probably going to come back to this sometime when I have more experience on building a data set, not just duckduckgo-ing photos.
It correctly identified my zinnias with 51% confidence and 43% being sure they were daisies, which I’ll count as a win.

1 Like

Your blog post link is dead, I would love to read it so much! Is there anywhere else I get to see your write up?

Thank you in advance!!!