The fastai book, published as Jupyter Notebooks
-
Updated
Oct 25, 2020 - Jupyter Notebook
{{ message }}
The fastai book, published as Jupyter Notebooks
The 3rd edition of course.fast.ai
Create delightful python projects using Jupyter Notebooks
An easy to use blogging platform, with enhanced support for Jupyter Notebooks.
Super easy library for BERT based NLP models
A site that displays up to date COVID-19 stats, powered by fastpages.
Temporary home for fastai v2 while it's being developed
Code For Medium Article: "How To Create Natural Language Semantic Search for Arbitrary Objects With Deep Learning"
Python supercharged for the fastai library
Practical Deep Learning for Time Series / Sequential Data library based on fastai v2/ Pytorch
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model Fine-tuning" https://arxiv.org/abs/1909.04761
Food detection and recommendation with deep learning
fastai V2 implementation of Timeseries classification papers.
中文ULMFiT 情感分析 文本分类
Starter app for fastai v3 model deployment on Render
FastAI PyTorch Serverless API (w/ AWS Lambda)
Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)
TensorDash is an application that lets you remotely monitor your deep learning model's metrics and notifies you when your model training is completed or crashed.
An API for identifying cougars v.s. bobcats v.s. other USA cat species
Some experiments with object detection in PyTorch
Plant Disease Detector Web Application
Docker environment for fast.ai Deep Learning Course 1 at http://course.fast.ai
A list of extensions for the fastai library.
Implementation of ULMFit algorithm for text classification via transfer learning
Deep Learning model to classify food (Web App)
Add a description, image, and links to the fastai topic page so that developers can more easily learn about it.
To associate your repository with the fastai topic, visit your repo's landing page and select "manage topics."
Before anything
Thank you for helping us build this amazing library❤️
First steps
The fastest way to learn the framework is by exploring the documentation and by playing around with the different tutorials (that are all available in colab).
The easiest way to start contributing is to start using the library and sharing your work with us (replying to this thread).