{"id":14959043,"url":"https://github.com/mind-the-pineapple/autoregressive-models","last_synced_at":"2025-06-27T10:07:09.131Z","repository":{"id":91831453,"uuid":"193794362","full_name":"Mind-the-Pineapple/Autoregressive-models","owner":"Mind-the-Pineapple","description":"Tensorflow 2.0 implementation of Deep Autoregressive Models","archived":false,"fork":false,"pushed_at":"2021-09-14T12:57:06.000Z","size":3506,"stargazers_count":27,"open_issues_count":0,"forks_count":3,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-06-27T10:06:55.812Z","etag":null,"topics":["autoregressive-neural-networks","gated-pixelcnn","generative-models","pixelcnn","pixelrnn","tensorflow","tensorflow-models","tensorflow2","vq-vae2"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Mind-the-Pineapple.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-06-25T23:00:36.000Z","updated_at":"2025-06-26T13:21:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"199f2527-7fb9-4fe6-9de6-75db0f2e6641","html_url":"https://github.com/Mind-the-Pineapple/Autoregressive-models","commit_stats":{"total_commits":128,"total_committers":7,"mean_commits":"18.285714285714285","dds":0.5625,"last_synced_commit":"34880e294b0999ddae77965f1f1b18528a7c5add"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Mind-the-Pineapple/Autoregressive-models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mind-the-Pineapple%2FAutoregressive-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mind-the-Pineapple%2FAutoregressive-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mind-the-Pineapple%2FAutoregressive-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mind-the-Pineapple%2FAutoregressive-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Mind-the-Pineapple","download_url":"https://codeload.github.com/Mind-the-Pineapple/Autoregressive-models/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mind-the-Pineapple%2FAutoregressive-models/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262235779,"owners_count":23279566,"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":["autoregressive-neural-networks","gated-pixelcnn","generative-models","pixelcnn","pixelrnn","tensorflow","tensorflow-models","tensorflow2","vq-vae2"],"created_at":"2024-09-24T13:18:45.404Z","updated_at":"2025-06-27T10:07:09.090Z","avatar_url":"https://github.com/Mind-the-Pineapple.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1 align=\"center\"\u003e Deep Autoregressive Models \u003c/h1\u003e\n\u003cp align=\"center\"\u003e\n\u003cimg height=\"250\" src=\"https://raw.githubusercontent.com/Mind-the-Pineapple/Autoregressive-models/master/1%20-%20Autoregressive%20Models%20-%20PixelCNN/figures/Figure6_reduced.png\"\u003e\n\u003c/p\u003e\n\n[![MIT license](http://img.shields.io/badge/license-MIT-brightgreen.svg)](https://github.com/Warvito/vq-vae/blob/master/LICENSE)\n\nThis repository is a supplement to our blog series *Deep Autoregressive Models*.\n\n## Setup\nClone the git repository :\n\n    git clone https://github.com/Mind-the-Pineapple/Autoregressive-models.git\n\nPython 3 with [TensorFlow 2.0+](https://www.tensorflow.org/) are the primary requirements.\nInstall virtualenv and create a new virtual environment:\n\n    sudo apt update\n    sudo apt install python3-dev python3-pip\n    sudo pip3 install -U virtualenv  # system-wide install\n    virtualenv --system-site-packages -p python3 ./venv\n\nThen, install requirements\n\n    source ./venv/bin/activate\n    pip3 install --upgrade pip\n    pip3 install -r requirements.txt\n\n--------------------------------------------------------------------------------------------------------------------------------------------------------------------\n\u003ch1 align=\"center\"\u003e 1. Autoregressive Models — PixelCNN \u003c/h1\u003e\n\u003cimg align=\"right\" width=\"500x\" src=\"https://raw.githubusercontent.com/Mind-the-Pineapple/Autoregressive-models/master/1%20-%20Autoregressive%20Models%20-%20PixelCNN/figures/Figure5_Architecture_reduced.png\"\u003e\n\nCreating digits with deep generative models!\n- [PixelCNN Medium Story](https://towardsdatascience.com/autoregressive-models-pixelcnn-e30734ede0c1)\n- [Google Colab](https://colab.research.google.com/github/Mind-the-Pineapple/Autoregressive-models/blob/master/1%20-%20Autoregressive%20Models%20-%20PixelCNN/pixelCNN.ipynb)\n- [Code](https://github.com/Mind-the-Pineapple/Autoregressive-models/blob/master/1%20-%20Autoregressive%20Models%20-%20PixelCNN/pixelCNN.py)\n- [Paper -\u003e Pixel Recurrent Neural Networks](https://arxiv.org/abs/1601.06759)\n\n\n\u003cbr\u003e\n\u003cbr\u003e\n\u003ch1 align=\"center\"\u003e 2. Modelling Coloured Images \u003c/h1\u003e\n\u003cimg align=\"right\" width=\"500x\" src=\"https://raw.githubusercontent.com/Mind-the-Pineapple/Autoregressive-models/master/2%20-%20Modelling%20data%20with%20multiple%20channels/figures/PixelcnnRGB.png\"\u003e\n\n\nExtending the model to the full colour spectrum\n- [PixelCNN - RGB Medium Story](https://blog.usejournal.com/modelling-coloured-images-acd0ebde0102)\n- [Google Colab](https://colab.research.google.com/gist/PedroFerreiradaCosta/a770317efa23f36b3c5009a9f21169f3/pixelcnn-rgb.ipynb?authuser=1#scrollTo=deJgSHmOBGfk)\n- [Code](https://github.com/Mind-the-Pineapple/Autoregressive-models/blob/master/2%20-%20Modelling%20data%20with%20multiple%20channels/pixelCNN_RGB.py)\n- [Paper -\u003e Pixel Recurrddent Neural Networks](https://arxiv.org/abs/1601.06759)\n\n\u003cbr\u003e\n\u003cbr\u003e\n\u003cbr\u003e\n\u003ch1 align=\"center\"\u003e 3. PixelCNN's Blind Spot and how to fix it \u003c/h1\u003e\n\u003cimg align=\"right\" width=\"500x\" src=\"https://raw.githubusercontent.com/Mind-the-Pineapple/Autoregressive-models/master/3%20-%20PixelCNNs%20Blind%20spot%20and%20Gated%20PixelCNNs/figures/results.png\"\u003e\n\nHow to fix the Pixel CNN's blind spot\n- [PixelCNN Medium Story](https://towardsdatascience.com/pixelcnns-blind-spot-84e19a3797b9)\n- [Google Colab](https://colab.research.google.com/github/Mind-the-Pineapple/Autoregressive-models/blob/master/3%20-%20PixelCNNs%20Blind%20spot%20and%20Gated%20PixelCNNs/PixelCNN_Blind_spot.ipynb)\n- [Code](https://github.com/Mind-the-Pineapple/Autoregressive-models/blob/master/3%20-%20PixelCNNs%20Blind%20spot%20and%20Gated%20PixelCNNs/pixelcnn_blind_spot.py)\n- [Paper -\u003e Gated PixelCNNs](https://arxiv.org/abs/1606.05328)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmind-the-pineapple%2Fautoregressive-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmind-the-pineapple%2Fautoregressive-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmind-the-pineapple%2Fautoregressive-models/lists"}