{"id":18903961,"url":"https://github.com/dudeperf3ct/fellowship.ai-challenges","last_synced_at":"2025-04-15T03:34:06.125Z","repository":{"id":191864877,"uuid":"172272236","full_name":"dudeperf3ct/fellowship.ai-challenges","owner":"dudeperf3ct","description":"This repo contains implementations of the challenges from fellowship.ai. For more, visit here. ","archived":false,"fork":false,"pushed_at":"2019-07-11T05:17:07.000Z","size":10450,"stargazers_count":6,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-28T15:21:28.919Z","etag":null,"topics":["few-shot-learning","food-101","maml","transfer-learning","transfer-learning-nlp","twitter-sentiment-analysis"],"latest_commit_sha":null,"homepage":"https://fellowship.ai/challenge","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dudeperf3ct.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-02-23T22:45:35.000Z","updated_at":"2023-07-20T20:01:51.000Z","dependencies_parsed_at":"2023-09-01T07:27:07.393Z","dependency_job_id":null,"html_url":"https://github.com/dudeperf3ct/fellowship.ai-challenges","commit_stats":null,"previous_names":["dudeperf3ct/fellowship.ai-challenges"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dudeperf3ct%2Ffellowship.ai-challenges","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dudeperf3ct%2Ffellowship.ai-challenges/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dudeperf3ct%2Ffellowship.ai-challenges/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dudeperf3ct%2Ffellowship.ai-challenges/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dudeperf3ct","download_url":"https://codeload.github.com/dudeperf3ct/fellowship.ai-challenges/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249002578,"owners_count":21196644,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["few-shot-learning","food-101","maml","transfer-learning","transfer-learning-nlp","twitter-sentiment-analysis"],"created_at":"2024-11-08T09:06:57.504Z","updated_at":"2025-04-15T03:34:05.020Z","avatar_url":"https://github.com/dudeperf3ct.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Select Your Challenge Problem\n\n## One-shot Learning\n\n[Omniglot](https://github.com/brendenlake/omniglot), the “transpose” of MNIST, with 1623 character classes, each with 20 examples. \n\nUse background set of [30 alphabets](https://github.com/brendenlake/omniglot/blob/master/python/images_background.zip) for training and evaluate on set of [20 alphabets](https://github.com/brendenlake/omniglot/blob/master/python/images_evaluation.zip). Refer to this [script](https://github.com/brendenlake/omniglot/blob/master/python/one-shot-classification/demo_classification.py) for sampling setup.\n\nReport one-shot classification (20-way) results using a meta learning approach like [MAML](https://arxiv.org/pdf/1703.03400.pdf).\n\n## Image Segmentation\n\nApply an automatic portrait segmentation model (aka image matting) to [celebrity face](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html) dataset. \n\n\n## Food-101\n\n[Food-101](https://www.vision.ee.ethz.ch/datasets_extra/food-101/) is a challenging vision problem, but everyone can relate to it.  Recent SoTA is ~80% top-1, 90% top-5.  These approaches rely on lots of TTA, large networks and  even novel architectures.\n\nTrain a decent model \u003e85% accuracy for top-1 for the test set, using a ResNet50 or smaller network with a reasonable set of augmentations.   \n\n\n## ULMFiT Sentiment \n\nApply a supervised or semi-supervised [ULMFiT](http://nlp.fast.ai/classification/2018/05/15/introducting-ulmfit.html) model to [Twitter US Airlines Sentiment](https://www.kaggle.com/crowdflower/twitter-airline-sentiment#Tweets.csv).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdudeperf3ct%2Ffellowship.ai-challenges","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdudeperf3ct%2Ffellowship.ai-challenges","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdudeperf3ct%2Ffellowship.ai-challenges/lists"}