Just wrote an article on nbdev. Let me know what you think 
5 Likes
Hi everyone, I created a step by step tutorial about integrating fast.ai with react and flask. This tutorial also builds a web application that enables login by face recognition.
6 Likes
Awesome. I’ve been planning to get started with some frontend work for a while, your article will certainly help me
2 Likes
Hi peter.rusznak Great work.
Flask is one of my favourite frameworks, as it’s very usable and the basics of the framework are not to difficult to understand. Also I think it is easier than Starlette and it has a large following. This will help a lot of people to integrate fastai with flask and javascript.
Cheers mrfabulous1 
Most of the datasets are noisy and incorrectly labelled. Sharing an example notebook to show case how to detect and clean noisy labels in the disaster tweets text dataset [1] can improve the accuracy(0.79 -> 0.85). This is done after detecting and removing the noisy labels using cleanlab [2]. For more information, refer Confident Learning [3]
[1] https://www.kaggle.com/c/nlp-getting-started
[2] https://github.com/cgnorthcutt/cleanlab
[3] Confident Learning: Estimating Uncertainty in Dataset Labels
4 Likes
Thank you for the tutorial, good job !
1 Like
For those who prefer Angular over React I created a new Tutorial about the integration of a trained model
I have started a blog with fastpages. My first post is about Noisy Imagenette, a version of Imagenette that comes with noisy labels. A training baseline is provided here
4 Likes
Here is my Bear Classification Project. It isn’t unique but I worked through all kinds of errors to get it up and running this past week so I have to just put it out there!
I Iearned so much about environments, github, and how libraries work! Thank you so much for the awesome course Jeremy!
1 Like
Hey guys!
Using the knowledge I got from Colaboratory Filtering chapter. I decided to go ahead and create a book recommendation app and deployed it on Streamlit. The app also automatically gives the links to the suggested books that can be opened in GoodReads.
Take a look and play around with it.
Here are the relevant links:
App: https://share.streamlit.io/jimmiemunyi/similarbooks/main/similar_books.py
Blog: https://jimmiemunyi.github.io/blog/tutorial/2021/02/15/Book-Recommendation-Model-Training.html
github: https://github.com/jimmiemunyi/SimilarBooks
6 Likes
After releasing my (undocumented) ULMFiT notebooks a while ago, I received a couple requests and questions about pertaining a language model from scratch. So I created a well documented repo on how to train ULMFiT models with SentencePiece. it covers the following steps:
- Preparing a wikipedia dump (in a docker container to avoid the hassle with wikiextractor)
- pretrain a Language model on Wikipedia
- Fine tune the LM on the downstream corpus
- Train a classifier
- Make predictions using the classifier / interpretation with fastinference
I also provide a pretrained German model.
Everyone talks about BERT and Transformers but for classification ULMFiT is still very close to SOTA (e.g. F1 score unoptimized ULMFiT 52,54 vs BERT 53.59 on GermEval2019). Fine tuning + training the classifier takes about 30 minutes.
Right now I’m trying to get SHA-RNN (https://arxiv.org/abs/1911.11423) integrated with fastai. So if someone would like to join me, please get in touch :).
11 Likes
This is my Poke-App. I found ~10000 images of pokemon from the first generation, and trained it in Pytorch originally. I then did it in FastAI and it was much faster and more pleasant. Please feel free to try it out. I was getting ~91% accuracy on first generation pokemon.
1 Like
Nice work! 
2 Likes
@lukew Much appreciated! I should give credit to the awesome dataset I found on Kaggle. I had to use resnet101 to get much above 92%… I accidently deleted the notebook, but fastai made this so much more compact than the pure pytorch one I had built earlier. My kids have been testing pictures of politicians, pokemon, and themselves. It seems to guess starmie or machamp for most people.
1 Like
Did you try with the other resnet depths, and did they perform better or worse?
What happens when there is no result? Have you considered having a null class?! 
Also – how would you get it to work on multiple positive predictions? 
Hi all,
Inspired by this, I made a sample notebook that shows you how to train raw Pytorch models with pytorch datasets and dataloaders on multi core TPUs on Colab using fastai and the fastai_xla_extensions packages to provide the training loop.
Check out the notebook here: https://colab.research.google.com/github/butchland/fastai_xla_extensions/blob/master/samples/minimal_fastai_pytorch_tpu_sample.ipynb
Best regards,
Butch
6 Likes
Yes, Tried 18, 34 and 50 and wasn’t happy with the accuracy of them. 101 got me above 91%. I’ve considered the null category – especially when I passed in a picture of a certain senate minority leader and it delivered the result of a Chancey. Just need some time. I’m doing this mostly at night and my youngest hasn’t always been cooperative!
I’d like to also test thresholds for determination and do an AUC for that.
1 Like
I have worked on implementing FixMatch for semi-supervised learning as a callback.
A complete example can be found here
Next step is to see how it performs on Imagewang. Hope it can make it to the leaderboard 
Currently, rand_augment_transform from timm is being used.
Any suggestions on how to integrate batch augmentations on the gpu?
Thanks,
7 Likes
I went down the rabbit hole of implementing landmark/keypoint regression using heatmaps with fastai v2, and ended up writing it up in a notebook-powered blog post. It covers the Heatmap Regression via Randomized Rounding paper (or at least, what I think that paper is doing - they’ve only posted inference code so the rest is my interpretation), with a HRNet backbone. Hope it’s useful to someone, suggestions / comments always welcome!
Link in case that first one wasn’t obvious: https://elte.me/2021-03-10-keypoint-regression-fastai
9 Likes
This is absolutely amazing!!! I tried doing this moons ago, and I’m so glad someone got it implemented. This is seriously an amazing implementation. Very well done!
4 Likes