{"id":13723469,"url":"https://github.com/michaelmendoza/learning-tensorflow","last_synced_at":"2025-06-25T06:33:47.007Z","repository":{"id":30414320,"uuid":"110883053","full_name":"michaelmendoza/learning-tensorflow","owner":"michaelmendoza","description":"Simple Tensorflow tutorials for learning by example","archived":false,"fork":false,"pushed_at":"2022-08-04T16:48:17.000Z","size":400,"stargazers_count":18,"open_issues_count":0,"forks_count":8,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-10T20:28:59.860Z","etag":null,"topics":["cifar10","convolutional-networks","deep-learning","example","fft","fourier-transform","keras","keras-tensorflow","keras-tutorials","learning-algorithms","learning-tensorflow","mnist-classification","neural-network","python","segmentation","tensorflow","tensorflow-tutorial","tensorflow2","tutorial","unet"],"latest_commit_sha":null,"homepage":"","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/michaelmendoza.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}},"created_at":"2017-11-15T20:29:36.000Z","updated_at":"2022-02-01T14:34:23.000Z","dependencies_parsed_at":"2022-08-07T15:15:28.210Z","dependency_job_id":null,"html_url":"https://github.com/michaelmendoza/learning-tensorflow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/michaelmendoza/learning-tensorflow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelmendoza%2Flearning-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelmendoza%2Flearning-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelmendoza%2Flearning-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelmendoza%2Flearning-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/michaelmendoza","download_url":"https://codeload.github.com/michaelmendoza/learning-tensorflow/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelmendoza%2Flearning-tensorflow/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261819437,"owners_count":23214502,"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":["cifar10","convolutional-networks","deep-learning","example","fft","fourier-transform","keras","keras-tensorflow","keras-tutorials","learning-algorithms","learning-tensorflow","mnist-classification","neural-network","python","segmentation","tensorflow","tensorflow-tutorial","tensorflow2","tutorial","unet"],"created_at":"2024-08-03T01:01:41.825Z","updated_at":"2025-06-25T06:33:46.971Z","avatar_url":"https://github.com/michaelmendoza.png","language":"Jupyter Notebook","readme":"# Learning Tensorflow\n![Supports TFv2.0](https://img.shields.io/badge/Supports-tensorflow%20v2.0-blue.svg)\n\nThis tutorial was created for learning tensorflow by example. Currently this repo contains examples for a simple single-layer neural network, a multi-layered perception neural network, and a convolutional neural network. Tensorflow implementations in this repo work with a variety of data sets. Included are simple examples using keras sequential API and more advanced examples using the imperative style of creating networks with model subclassing API.\n\n### Getting Started\nInstallation requires python 3 with tensorflow. The easiest method to install the requisite libraries is to install the [conda package manager](https://conda.io/miniconda.html). Then run the following command to install necessary libraries and create a virtual environment call `tf`:\n\n```\nconda create -n tf python=3.6 numpy matplotlib scikit-image tqdm pycairo\n```\n\nIf you have a CUDA-enabled GPU install tensorflow-gpu: `pip install tensorflow-gpu`\nOtherwise use: `pip install tensorflow`\n\nActivate this virtual environment with `source activate tf` (Mac) or `activate tf` (PC).\n\n### Notes\n\n**Update**: Updated examples for use with tensorflow 2.0!\n\nIf you are using older version of Tensorflow like 1.12, please look [here](https://github.com/michaelmendoza/learning-tensorflow/blob/tf-v1.12/README.md)\n\n# Examples\nExamples of tensorflow implementations for Classification, Segmentation, Regression and Modeling Fourier Transform\n\n## Basics\n\nPython basics ([tutorial](notebooks/0a%20-%20Python%20Basics.ipynb))\n\n## Regression\nLinear regression from scatch with Tensorflow 2.0 ([tutorial](/notebooks/0b%20-%20Regression%20from%20Scratch%20with%20Tensorflow.ipynb))\n\nNon-linear regression with Tensorflow 2.0 and Keras API ([tutorial](notebooks/0c%20-%20Regression%20with%20Tensorflow%20and%20Keras%20API.ipynb))\n\n## Classification\nA variety of neural network implementations for MNIST, and CFAR-10 datasets for classification\n\n### MNIST\nClassifying using MNIST Dataset\n\n- Basic Neural Network from scatch with Tensorflow 2.0 ([tutorial](notebooks/1a%20-%20Simple%20Neural%20Network.ipynb))\n- Basic Neural Network with simple Keras APIs ([tutorial](notebooks/1b%20-%20Simple%20Neural%20Network%20with%20Keras.ipynb))\n- Multi-layer Neural Nework ([simple](examples/mnist/mnist1.py), [advanced](examples/mnist/mnist1_imperative.py)) - A simple (multi-layer preception) network for classifying MNIST dataset \n- Convolutional Neural Nework ([simple](examples/mnist/mnist2.py), [advanced](examples/mnist/mnist2_imperative.py)) - A convolutional network for classifying MNIST dataset \n\n### CIFAR-10\n- Basic Neural Network ([code](examples/cifar/cifar0.py)) - A simple (single layer preception) network for classifying CIFAR-10 dataset \n- Multi-layer Neural Nework ([code](examples/cifar/cifar1.py)) - A simple (multi-layer preception) network for classifying CIFAR-10 dataset \n- Convolutional Neural Nework ([code](examples/cifar/cifar2.py)) - A convolutional network for classifying CIFAR-10 dataset\n- Convolutional Neural Nework ([code](examples/cifar/cifar3.py)) - A convolutional network (6-conv, 3 max pool, 2 fully-connected layers) with Dropout for classifying CIFAR-10 dataset \n- VGG network ([code](examples/cifar/cifar4.py), [paper](https://arxiv.org/pdf/1409.1556v6.pdf)) - A very deep convolutional network for large-scale image recongition\n\n## Segmentation\nTensorflow implementation for simple color segmentation using a Unet ([tutorial](notebooks/Segmentation.ipynb))\n\n## Modeling Fourier Transform / FFT\nNeural network implementation for learning a fourier transform ([code](examples/fft/fft.py))\n","funding_links":[],"categories":["Libraries and Frameworks","Jupyter Notebook"],"sub_categories":["Other Languages"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmichaelmendoza%2Flearning-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmichaelmendoza%2Flearning-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmichaelmendoza%2Flearning-tensorflow/lists"}