{"id":15639972,"url":"https://github.com/hereismari/tensorflow-maml","last_synced_at":"2025-04-30T07:24:58.092Z","repository":{"id":88345753,"uuid":"180441132","full_name":"hereismari/tensorflow-maml","owner":"hereismari","description":"TensorFlow 2.0 implementation of MAML.","archived":false,"fork":false,"pushed_at":"2019-07-12T20:03:49.000Z","size":2368,"stargazers_count":83,"open_issues_count":2,"forks_count":21,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-30T13:51:16.248Z","etag":null,"topics":["eager-execution","maml","meta-learning","tensorflow","tensorflow2"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hereismari.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-04-09T20:05:55.000Z","updated_at":"2024-11-28T13:13:45.000Z","dependencies_parsed_at":null,"dependency_job_id":"da450a0a-1bb2-418d-9528-9badd8c3fc80","html_url":"https://github.com/hereismari/tensorflow-maml","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hereismari%2Ftensorflow-maml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hereismari%2Ftensorflow-maml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hereismari%2Ftensorflow-maml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hereismari%2Ftensorflow-maml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hereismari","download_url":"https://codeload.github.com/hereismari/tensorflow-maml/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251659470,"owners_count":21623053,"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":["eager-execution","maml","meta-learning","tensorflow","tensorflow2"],"created_at":"2024-10-03T11:29:15.106Z","updated_at":"2025-04-30T07:24:58.071Z","avatar_url":"https://github.com/hereismari.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Reproduction of MAML using TensorFlow 2.0.\n\nThis reproduction is highly influenced by the pytorch reproduction by Adrien Lucas Effot available at [Paper repro: Deep Metalearning using “MAML” and “Reptile”](https://towardsdatascience.com/paper-repro-deep-metalearning-using-maml-and-reptile-fd1df1cc81b0).\n\n**MAML**   |   **Neural Net**\n\n![alt-text-1](imgs/maml.png \"MAML\") ![alt-text-2](imgs/nn.png \"Neural Net\")\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"350\" height=\"250\" src=\"imgs/maml_vs_nn.png\"\u003e\n\u003c/p\u003e\n\n## MAML paper\n\nhttps://arxiv.org/abs/1703.03400\n\n**Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks**\n*Chelsea Finn, Pieter Abbeel, Sergey Levine*\n\n\u003e We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies.\n\n---\n\n![image.png](https://cdn-images-1.medium.com/max/1600/1*EUt0H5AOEFkERg-OzfCC7A.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhereismari%2Ftensorflow-maml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhereismari%2Ftensorflow-maml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhereismari%2Ftensorflow-maml/lists"}