Hi,
It’s been awhile since I have not read all the posts in the Share Your Work Here thread that are all about models and applications created using fastai v1. It’s IMPRESSIVE!!!
As I wanted to show some examples to a group that is learning Deep Learning in the university of Brasilia (UnB), I made a copy/paste list of projects that seemed interesting.
I apologize by advance to all those who will not find their project in this list (I quickly reviewed the 1586 posts of this thread…) but thanks to Jeremy, you can now update yourself this list
Congratulations to all! Very inspiring.
How to update this list?
Anyone with a published fastai project can now update the following list with the link to his/her post explaining the project and a short description. In addition, put keywords to facilitate quick search of your project.
- (image, drawing) classify drawings in the Quick Draw competition: Share your work here ✅ and Share your work here ✅
- (image, food) classify food pictures from the food-101 75 dataset: Share your work here ✅ and Share your work here ✅
- (image, forest) a big forest/nature related dataset to build an image classifier on: Share your work here ✅
- (image, food) classify food pictures from the food-101 75 dataset: Share your work here ✅
- (image, fashion) DeepFashion classifier: Share your work here ✅
- (audio) audio classification: Share your work here ✅
- (image, city) classification of cultural urban characteristics: Share your work here ✅
- (image, art) classification of painters styles: Share your work here ✅
- (audio) Urban Sounds database: Share your work here ✅
- (audio) Freesound General-Purpose Audio Tagging Challenge: Share your work here ✅
- (text) text classifier, which is able to detect language of handwritten document based on images: Share your work here ✅
- (image, bird) the Birds dataset from Caltech 14. It seems going to be challenging, there is 200 bird classes each a dozen pictures: Share your work here ✅
- (image, city) classification model with street pictures from SF, NYC, Tokyo, and Paris: Share your work here ✅
- (image, driver → security, seguros) Distracted Driver Detection: Share your work here ✅
- (audio, voice) voice recognition detection: Share your work here ✅
- (image, hostel) classify hostel and hotel rooms: Share your work here ✅
- (image, bird) Birds images classification: Share your work here ✅
- (audio, sound) sounds classification Share your work here ✅
- (image, building) segment & classify the condition of buildings seen on hi-res aerial (drone) imagery taken over Zanzibar island, Tanzania: Share your work here ✅, Share your work here ✅, Share your work here ✅ and Share your work here ✅
- (image, art painting) image model to identify the artist of a painting: Share your work here ✅
- (image, architecture) Architectural Heritage Elements image Dataset: Share your work here ✅
- (audio, spectrograms) classification of 149 different composers based on spectrograms of their compositions: Share your work here ✅
- (image, politics) Senators Facial Recognition: Share your work here ✅
- (image, satelite) satellite project with webapp: yourcityfrom.space: Share your work here ✅, Share your work here ✅ and Share your work here ✅
- (image, food) healthy vs junk food detector app: Share your work here ✅
- (image, face recognition) Face Expression Recognition (FER): Share your work here ✅ and Share your work here ✅
- (image, sign language) American sign language dataset: Share your work here ✅ and Share your work here ✅
- (image, time series) Time series classification: General Transfer Learning with Convolutional Neural Networks: Share your work here ✅
- (image, road) image classification to classify stop, yield and school crossing: Share your work here ✅
- (image, biology) Kaggle “Human protein atlas” competition: Share your work here ✅
- (image, biology) an immune cell classifier: Share your work here ✅
- (image, brain) a binary image classifier to identify abnormal and normal brain images from MRs: Share your work here ✅
- (text, legal) a text classifier on legal judgments: Share your work here ✅
- (image, cancer) Cancer Type Classification using Gene Expression data: Share your work here ✅
- (image) CelebA dataset 11 from Kaggle for a regression model: Share your work here ✅
- collaborative filtering: Share your work here ✅
- facial keypoint detection 6 dataset from kaggle: Share your work here ✅
- (image, cancer) Classification of Tumor tissue using Deep Learning: Share your work here ✅
- (audio) audio classification, using bachir’s strategy of transforming the audio signal into an image represents its spectrogram, and then performing transfer learning on those images using the guidelines from the first three lessons: Share your work here ✅
- (image, skin cancer) Skin Cancer Classifier: Share your work here ✅
- (text) language model on 26 works of fiction from Project Gutenberg: Share your work here ✅
- (image, audio) classifying audio using image classifiers: https://forums.fast.ai/t/share-your-work-here/27676/628
- (text) Walt Whitman Poetry Generator app: https://forums.fast.ai/t/share-your-work-here/27676/654
- (image, food) Food Classifier: Mobile App: https://forums.fast.ai/t/share-your-work-here/27676/679
- (text) build a “Musk-like” Tweet generator trained with over 6,000 of his tweets from 2010–2018: https://forums.fast.ai/t/share-your-work-here/27676/710
- (image, GAN) add colors to a crap black & white image: https://forums.fast.ai/t/share-your-work-here/27676/718
- (image, colorization) colorizing black and white images using perceptual loss: https://forums.fast.ai/t/share-your-work-here/27676/743 and https://forums.fast.ai/t/share-your-work-here/27676/1083
- (image, satellite) in Kaggle in the PLAsTiCC Competition 5 for classifying astronomical objects: https://forums.fast.ai/t/share-your-work-here/27676/747
- (image, film) deep learning model to distinguish pictures from 10 animated classic movies (Disney’s The Little Mermaid, Beauty and the Beast, Pocahontas, Tarzan, Mulan, Hercules Disney and Ghibli studio’s Castle In The Sky, Howl’s Moving Castle, Kiki’s Delivery Service and Princess Mononoke): https://forums.fast.ai/t/share-your-work-here/27676/765
- (image, GAN) pre-trained GAN to turn images into cartoons: https://forums.fast.ai/t/share-your-work-here/27676/893
- (image, mosquito) classifier for mosquito species identification: https://forums.fast.ai/t/share-your-work-here/27676/898
- (image, cancer) predicting malignancy in tumors: https://forums.fast.ai/t/share-your-work-here/27676/957
- (image, cloud) multiclass cloud classifier and pushed it to production: https://forums.fast.ai/t/share-your-work-here/27676/958, https://forums.fast.ai/t/share-your-work-here/27676/1080, https://forums.fast.ai/t/share-your-work-here/27676/1593 and https://forums.fast.ai/t/share-your-work-here/27676/1451
- (image, game) Magic Sudoku 9, which scans and solves Sudoku puzzles and displays that solution over the top of the real one in AR: https://forums.fast.ai/t/share-your-work-here/27676/993
- (data) The competition 4 requires you to use tabular data to predict whether Santander bank customers will buy products in the future: https://forums.fast.ai/t/share-your-work-here/27676/1009
- (image, heart) identifying different pieces of cardiac anatomy inside real human hearts: https://forums.fast.ai/t/share-your-work-here/27676/1081
- (image, image similarity, art) a recommender system based on image similarity of the plates: https://forums.fast.ai/t/share-your-work-here/27676/1084
- (image, medicine) medical image classification: https://forums.fast.ai/t/share-your-work-here/27676/1088
- (image, art with GAN) compare baroque paintings with ancient Greek pottery paintings: https://forums.fast.ai/t/share-your-work-here/27676/1093
- (image, text) web app that gives you a witty caption when you upload a pic with a San Francisco landmark: https://forums.fast.ai/t/share-your-work-here/27676/1097
- (image, art style with GAN) Stylegan on a portrait art dataset and was thought the results were decent, this was through transfer learning: https://forums.fast.ai/t/share-your-work-here/27676/1098
- (image) web app for demonstrating the capabilities of the Poisonous plant classifier model: https://forums.fast.ai/t/share-your-work-here/27676/1100
- (image, whale) whale classifier: https://forums.fast.ai/t/share-your-work-here/27676/1102
- (data, mobile) project Deep Visual Semantic Embedding Models for Mobile: https://forums.fast.ai/t/share-your-work-here/27676/1109
- (image, age) age prediction: https://forums.fast.ai/t/share-your-work-here/27676/1127
- (image, fashion) Fashion MNIST dataset: https://forums.fast.ai/t/share-your-work-here/27676/1139 and https://forums.fast.ai/t/share-your-work-here/27676/1197
- (text) measure the tonality/sentiment of a tweet: https://forums.fast.ai/t/share-your-work-here/27676/1154
- (image, GAN) a super resolution model that restores movie poster images: https://forums.fast.ai/t/share-your-work-here/27676/1163
- (image, radiology) MURA is a dataset of bone X-rays that allows to create models that find abnormalities: https://forums.fast.ai/t/share-your-work-here/27676/1186
- (data, virus) Kaggle’s Microsoft Malware Prediction: https://forums.fast.ai/t/share-your-work-here/27676/1188
- (image, drawing, GAN) turn a pencil sketch into a real photo: https://forums.fast.ai/t/share-your-work-here/27676/1204
- (image, skin cancer) an app to classify skin cancer images and deployed it using Render: https://forums.fast.ai/t/share-your-work-here/27676/1220
- (image, plastic) website or app where you get information on whether the plastics are ready to recycle or not: https://forums.fast.ai/t/share-your-work-here/27676/1221
- (data) Predicting price action movement for currency pairs: https://forums.fast.ai/t/share-your-work-here/27676/1230
- (image, cancer) cellular histo-pathology image classification: https://forums.fast.ai/t/share-your-work-here/27676/1252
- (image, art with GAN) 9 GANS is An AI Generated Art Gallery: https://forums.fast.ai/t/share-your-work-here/27676/1340
- (text) Ask Roboflow, an AI trained to answer programming questions: https://forums.fast.ai/t/share-your-work-here/27676/1346
- (image, face) Kaggle Competition: Facial Keypoints Detection: https://forums.fast.ai/t/share-your-work-here/27676/1366
- (image, digit in real-time) Real Time Handwritten recognition CHALLENGE: https://forums.fast.ai/t/share-your-work-here/27676/1368
- (image, segmentation) egmentation using the data from the current iMaterialist (Fashion) 2019 at FGVC6 6 on Kaggle: https://forums.fast.ai/t/share-your-work-here/27676/1378
- (image, artist) kaggle artwork dataset of paintings by 50 artists and tried to classify the artist: https://forums.fast.ai/t/share-your-work-here/27676/1391
- (image, captcha) automatic captcha solving: https://forums.fast.ai/t/share-your-work-here/27676/1417
- (data) Using Image Recognition to Predict Stock Trends: https://forums.fast.ai/t/share-your-work-here/27676/1437
- (image, bird with GAN) model that can generate bird images from text description: https://forums.fast.ai/t/share-your-work-here/27676/1444
- (text, data, assistant) Next Best Action Prediction with Text and Metadata: Building an Agent Assistant: https://forums.fast.ai/t/share-your-work-here/27676/1465
- (data, text, code) web app that classifies text according to the programming language: https://forums.fast.ai/t/share-your-work-here/27676/1487
- (image, radiology) Deep learning can extract prognostic information about health and longevity embedded in routine medical imaging: https://forums.fast.ai/t/share-your-work-here/27676/1489
- (image) ShopNet: A Neural Network for Product Images: https://forums.fast.ai/t/share-your-work-here/27676/1514
- (image, art) basic art classifier that tells you the artistic movement: https://forums.fast.ai/t/share-your-work-here/27676/1526
- (image, blind people) Banknotes detection for blind people: https://forums.fast.ai/t/share-your-work-here/27676/1539
- (image, satellite) Remote Sensing Image Scene Classification: Benchmark and State of the Art (Cheng et al. 2017): https://forums.fast.ai/t/share-your-work-here/27676/1555
- (image, audio, bird) Bird Sound Classifier: https://forums.fast.ai/t/share-your-work-here/27676/1580
- (image, pill) image classifier to differentiate between 10 different medications: Allopurinol, Atenolol, Ciprofloxacin, Levothyroxine, Metformin, Olanzapine, Omeprazole, Oxybutynin, Prednisone, Rosuvastatin: https://forums.fast.ai/t/share-your-work-here/27676/1611
- (image, art) The app allows users to turn random pictures into paintings of 3 old masters Van Gogh, Monet and Cezanne: https://forums.fast.ai/t/share-your-work-here/27676/1628
- (image, colorisation) Introducing DeOldify: A Progressive, Self-Attention GAN based image colorization/restoration project
- (image, text, Devanagari handwritten) This article is about classifying handwritten Devanagari letters (much like hindi-version of MNIST) | https://forums.fast.ai/t/share-your-work-here/27676/1336 | medium: Devanagari Handwritten Image Classifier
- (image, Image Similarity Search) This article is about how to use Pytorch Hooks and Spotify Annoy to build a image classification model which gives similar images based on a given image | https://forums.fast.ai/t/share-your-work-here/27676/1497 | medium: Image Similarity Search using Fastai and Spotify Annoy
- (image, Image Similarity Search) image similarity search engine: https://forums.fast.ai/t/image-similarity-search/31174
- (GUI) Visual_UI : graphical user interface for fastai
- (image, film, custom-dataset) introducing a first of its kind dataset enabling quantitative analysis of film ⟶ cinema shot-type classifier ⟶ forum | interactive website (sliding heatmaps) | medium