How do I run these TensorFlow tutorials on my computer?

Install TensorFlow, NumPy, and other listed libraries via pip, download the VGG model into the 'data/' folder, and open the Jupyter Notebooks to execute code interactively.

Are these tutorials good for someone with no machine learning experience?

Yes, they start with basics like NumPy and TensorFlow operations, progressing slowly to advanced topics, but assume some Python knowledge.

sjchoi86/TensorFlow-101 vs official TensorFlow tutorials: which is better?

This collection is more beginner-focused with kinder explanations and a recipe format, while official tutorials are more current but less hand-holding.

Can I use these with TensorFlow 2.x?

The tutorials are based on older TensorFlow versions and might need code modifications for TensorFlow 2.x compatibility, as they're not explicitly updated.

How to create custom datasets using these notebooks?

Refer to notebooks like 'basic_gendataset.ipynb' which teach custom dataset generation and preprocessing for TensorFlow models.

What are the hardware requirements for running these deep learning tutorials?

You need a decent GPU and sufficient RAM for training models, especially for advanced notebooks like CNNs and RNNs, though basics can run on CPUs.

Sungjoon's TensorFlow-101

MITJupyter Notebook

A collection of beginner-friendly TensorFlow tutorials using Jupyter Notebook, covering deep learning fundamentals and practical applications.

GitHub

What is Sungjoon's TensorFlow-101?

TensorFlow Tutorials is a collection of educational Jupyter Notebooks that teach TensorFlow and deep learning concepts to beginners. It provides step-by-step tutorials covering fundamental machine learning algorithms, neural network architectures, and practical applications like image processing and natural language processing. The project serves as a comprehensive learning resource that progresses from basic TensorFlow operations to advanced deep learning techniques.

Target Audience

Beginners learning TensorFlow and deep learning, data science students, and developers looking for practical, hands-on tutorials to understand machine learning concepts through interactive Jupyter Notebook examples.

Value Proposition

Developers choose these tutorials because they offer beginner-friendly explanations in an interactive notebook format, cover a wide range of topics from basics to advanced applications, and provide practical, runnable code examples that serve as a reference for real deep learning projects.

Overview

TensorFlow Tutorials

Use Cases

Best For

Learning TensorFlow fundamentals through hands-on Jupyter Notebook examples

Related Projects

Community-curated · Updated weekly · 100% open source

Found a gem we're missing?

Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.

Submit a project Star on GitHub

2.6k stars734 forks0 contributors

Understanding deep learning architectures like CNNs, RNNs, and auto-encoders

Practicing machine learning with custom dataset generation and processing

Exploring computer vision applications including image processing and neural style transfer

Learning how to use TensorBoard for model visualization and debugging

Getting started with natural language processing techniques like word embeddings

Not Ideal For

Developers needing tutorials with the latest TensorFlow 2.x APIs and Keras integration
Teams seeking production-ready code examples with deployment best practices
Projects requiring advanced topics like distributed training or model serving
Learners preferring structured video courses over self-paced Jupyter Notebooks

Pros & Cons

Pros

Beginner-Friendly Explanations

Tutorials are written 'as kindly as possible' with clear, accessible language aimed at TensorFlow newcomers, making complex topics approachable.

Comprehensive Topic Coverage

Spans over 16 categories from basics to advanced applications like semantic segmentation and neural style transfer, providing a wide learning path.

Interactive Notebook Format

All tutorials are Jupyter Notebooks, enabling hands-on experimentation and immediate feedback for better understanding.

Practical Real-World Examples

Includes notebooks on custom dataset generation, pre-trained VGG model usage, and TensorBoard visualization, offering applicable skills.

Cons

Potentially Outdated Code

Based on refactorings of older tutorials, it may not reflect TensorFlow 2.x features, requiring manual updates for modern use.

Complex Setup Requirements

Requires manual download of external dependencies like the pre-trained VGG model and multiple libraries, which can be cumbersome for beginners.

Incomplete Tutorials

Some notebooks, such as super resolution, are marked 'in progress', indicating gaps in coverage and reliability.

Frequently Asked Questions

Home

TensorFlow

TensorFlow Python Notebooks

TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

Stars43,779

Forks14,765

Last commit1 year ago

TensorFlow Tutorial 3

TensorFlow Tutorials with YouTube Videos

Stars9,276

Forks4,118

Last commit5 years ago

Effective Tensorflow

TensorFlow tutorials and best practices.

Stars8,598

Forks885

Last commit5 years ago

TensorFlow tutorials

Simple tutorials using Google's TensorFlow Framework

Stars6,026

Forks1,484

Last commit2 years ago

#tensorflow-tutorials

#computer-vision

#convolutional-neural-networks

#machine-learning

#recurrent-neural-networks

#educational-resource