# morvanzhou/tensorflow-tutorial

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/morvanzhou-tensorflow-tutorial).**

4,334 stars · 1,836 forks · Python · MIT

## Links

- GitHub: https://github.com/MorvanZhou/Tensorflow-Tutorial
- Homepage: https://mofanpy.com/tutorials/machine-learning/tensorflow/
- awesome-repositories: https://awesome-repositories.com/repository/morvanzhou-tensorflow-tutorial.md

## Topics

`autoencoder` `classification` `cnn` `deep-q-network` `dqn` `dropout` `gan` `generative-adversarial-network` `machine-learning` `neural-network` `regression` `rnn` `tensorflow` `tensorflow-tutorials` `tutorial`

## Description

This project is a collection of educational resources and reference implementations for neural network development using TensorFlow. It serves as a comprehensive learning course, machine learning curriculum, and practical implementation guide for building deep learning architectures.

The codebase provides instructional materials and examples covering a wide range of model types, including convolutional neural networks for image classification, recurrent networks and long short-term memory cells for sequential data, and autoencoders for generative modeling. It also includes implementations for deep reinforcement learning agents and transfer learning techniques for adapting pre-trained models to new tasks.

The project covers the full development lifecycle, including data preprocessing, computational graph definition, and weight optimization. It provides utilities for model evaluation and training optimization, such as dropout and regularization, alongside tools for visualizing network architecture and monitoring training metrics.

## Tags

### Artificial Intelligence & ML

- [Neural Network Training](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-training.md) — Provides reference implementations for adjusting internal weights via iterative cycles to minimize prediction error. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/create-NN))
- [Activation Functions](https://awesome-repositories.com/f/artificial-intelligence-ml/activation-functions.md) — Implements mathematical functions to introduce non-linearity into neural network models via element-wise activation mappings. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/activation))
- [Computational Graph Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/computational-graph-definitions.md) — Constructs data flow graphs where nodes represent mathematical operations to define the computation pipeline. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/structure))
- [Convolutional Feature Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-feature-extraction.md) — Implements convolutional layers and pooling operations to extract spatial patterns from image data.
- [Convolutional Neural Network Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-network-architectures.md) — Constructs deep convolutional neural network architectures using pooling and activations for image classification. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/CNN3))
- [Activation Functions](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks/activation-functions/relu-activations/activation-functions.md) — Applies mathematical functions like ReLU and Sigmoid to introduce non-linearity into neural network layers. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-activation-function))
- [Deep Learning Training Toolsets](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-learning-training-toolsets.md) — Provides a full toolset for training, optimizing, and iterating on deep neural networks. ([source](https://cdn.jsdelivr.net/gh/morvanzhou/tensorflow-tutorial@master/README.md))
- [Fully Connected Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/fully-connected-layers.md) — Implements dense layers that perform linear transformations using matrix multiplication and bias offsets for predictions. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/CNN3))
- [Loss Function Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/loss-function-implementations.md) — Implements various loss functions to calculate the error between predictions and actual values for minimization via gradient descent. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/classifier))
- [Convolution Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/convolution-layers.md) — Implements convolutional layers that apply sliding window filters to extract spatial features from image data. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/CNN2))
- [LSTM Sequence Models](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/recurrent-layers/recurrent-model-definitions/lstm-sequence-models.md) — Implements recurrent network architectures specifically utilizing Long Short-Term Memory cells for sequential data processing. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-LSTM))
- [Sequential Data Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/sequential-containers/recurrent-state-managers/sequential-data-processing.md) — Implements sequential data processing where current outputs depend on previous internal states using recurrent networks and LSTM cells. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-RNN))
- [Pre-trained Weight Adaptation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning/pre-trained-model-zoos/model-adaptation-frameworks/pre-trained-weight-adaptation.md) — Provides techniques for initializing models with pre-trained weights and replacing final layers for new classification tasks. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/transfer-learning))
- [Neural Network Construction](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-construction.md) — Provides a comprehensive guide to designing and building deep learning architectures using various layers and model abstractions. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/create-NN))
- [Neural Network Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-implementations.md) — Provides reference implementations of various neural network architectures and transfer learning techniques.
- [Neural Network Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-layers.md) — Implements custom neural network layers with randomized weights for matrix multiplication and activation. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/add-layer))
- [Training Execution Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-training-pipelines/training-execution-loops.md) — Manages the full training process including parameter initialization and execution loops within a session. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/example2))
- [Activation Functions](https://awesome-repositories.com/f/artificial-intelligence-ml/non-linear-classifiers/activation-functions.md) — Uses non-linear activation functions to enable the modeling of complex relationships within neural networks.
- [Gradient Descent Algorithms](https://awesome-repositories.com/f/artificial-intelligence-ml/optimization-algorithms/gradient-descent-algorithms.md) — Implements iterative parameter updates using gradient descent algorithms to minimize loss functions.
- [Parameter Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/parameter-optimizers.md) — Implements gradient-based algorithms to update model weights and minimize loss during training. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/tf-gradient-descent))
- [Recurrent Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/recurrent-neural-networks.md) — Provides implementations of recurrent neural network architectures designed for processing sequential data and time-series prediction. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/RNN3))
- [Training Optimization Techniques](https://awesome-repositories.com/f/artificial-intelligence-ml/training-optimization-techniques.md) — Provides detailed implementations of optimizers and regularization strategies to improve neural network convergence and accuracy. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/))
- [Transfer Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/transfer-learning.md) — Implements techniques for adapting pre-trained models to new tasks by modifying model heads while retaining learned weights. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/))
- [Convolutional Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks.md) — Implements convolutional neural networks that use convolutional and pooling layers to extract spatial features. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/CNN1))
- [Data Preparation](https://awesome-repositories.com/f/artificial-intelligence-ml/data-preparation.md) — Provides utilities for cleaning, normalizing, and generating synthetic training data with noise. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/create-NN))
- [Deep Reinforcement Learning Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-q-learning-implementations/deep-reinforcement-learning-implementations.md) — Implements functional deep reinforcement learning agents using Deep Q-Networks.
- [Dropout Regularization](https://awesome-repositories.com/f/artificial-intelligence-ml/dropout-regularization.md) — Implements random neuron deactivation to prevent overfitting and reduce reliance on specific neurons. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-overfitting))
- [Latent Space Compression](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models/latent-space-projections/latent-space-encoders/latent-space-compression.md) — Provides techniques for compressing high-dimensional input into compact latent representations using autoencoders.
- [Generative Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-models.md) — Develops generative architectures for synthesizing new data using encoding and adversarial techniques. ([source](https://cdn.jsdelivr.net/gh/morvanzhou/tensorflow-tutorial@master/README.md))
- [High-Level Model APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/high-level-model-apis.md) — Provides declarative interfaces for constructing neural networks through modular components and high-level abstractions. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/tf2017))
- [Image Classification](https://awesome-repositories.com/f/artificial-intelligence-ml/image-classification.md) — Provides implementations for categorizing visual content into predefined classes using convolutional neural networks.
- [Predictive Machine Learning Analytics](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/algorithms/predictive-machine-learning-analytics.md) — Produces outputs for new inputs using learned patterns to perform predictive machine learning analytics. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/what-does-NN-do))
- [Normalization Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/normalization-layers.md) — Utilizes normalization layers to standardize input activations, stabilizing training and improving convergence. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/BN))
- [Recurrent State Managers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/sequential-containers/recurrent-state-managers.md) — Manages cell state passing in recurrent networks to maintain temporal dependencies across batches.
- [Training Monitoring Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/training-monitoring-and-profiling/training-observability-systems/training-monitoring-tools.md) — Monitors internal weight distributions and loss trends using histograms and scalar summaries. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/RNN4))
- [Model Training Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training-optimizers.md) — Implements techniques like dropout and batch normalization to accelerate training convergence and stabilize model performance. ([source](https://cdn.jsdelivr.net/gh/morvanzhou/tensorflow-tutorial@master/README.md))
- [Autoencoders](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-implementations/autoencoders.md) — Implements autoencoder architectures for compressing high-dimensional data into latent spaces. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/autoencoder))
- [Neural Network Visualizations](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-visualizations.md) — Generates graphical representations of neural network architectures and topologies to inspect the model framework. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/tensorboard1))
- [Overfitting Reduction Techniques](https://awesome-repositories.com/f/artificial-intelligence-ml/overfitting-reduction-techniques.md) — Implements regularization techniques such as dropout to improve model generalization and prevent overfitting. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/CNN3))
- [Pre-trained Model Transfer](https://awesome-repositories.com/f/artificial-intelligence-ml/pre-trained-model-transfer.md) — Implements methods for adapting pre-trained model backbones by resetting and updating only the final output layers. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/transfer-learning))
- [Predictive Modeling](https://awesome-repositories.com/f/artificial-intelligence-ml/predictive-modeling.md) — Implements various predictive and generative algorithms to solve diverse data tasks. ([source](https://mofanpy.com/))
- [Sequence Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-learning-models/sequence-model-training.md) — Provides training procedures that optimize weights using gradient-based optimizers for sequence-based models. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/RNN2))
- [Sequence-to-Sequence Models](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-to-sequence-models.md) — Implements encoder-decoder neural network architectures to transform input sequences into target sequences for translation tasks. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-RNN))
- [Sequential Data Classification](https://awesome-repositories.com/f/artificial-intelligence-ml/sequential-data-models/sequential-data-classification.md) — Applies sequential models to categorize input data sequences based on the cumulative state of the network. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-RNN))
- [Sequential Text Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/sequential-text-generation.md) — Implements techniques for predicting subsequent tokens in a sequence using recurrent architectures for structured content generation. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-RNN))
- [Model Weight Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/tensorflow-model-development/model-weight-persistence.md) — Implements techniques for saving and loading trained weights within the TensorFlow ecosystem. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/))
- [Pre-trained Neural Feature Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/text-feature-extraction/pre-trained-neural-feature-extraction.md) — Extracts high-dimensional feature vectors from raw data using layers from pre-trained neural networks. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-feature-representation))
- [Training Convergence Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/training-convergence-optimization.md) — Implements optimization algorithms like Adam and SGD to accelerate the speed of model training convergence. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-speed-up-learning))
- [Training Convergence Visualizations](https://awesome-repositories.com/f/artificial-intelligence-ml/training-convergence-visualizations.md) — The project plots parameter movement and cost reduction to analyze convergence and learning rates. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/tf-gradient-descent))
- [Weight Regularization](https://awesome-repositories.com/f/artificial-intelligence-ml/weight-regularization.md) — Implements L1 and L2 norm penalties on model weights to prevent overfitting and improve generalization. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-overfitting))

### Education & Learning Resources

- [Deep Learning Courses](https://awesome-repositories.com/f/education-learning-resources/deep-learning-courses.md) — Comprehensive educational course for mastering TensorFlow from basic concepts to advanced deep learning architectures.
- [Deep Learning Education](https://awesome-repositories.com/f/education-learning-resources/deep-learning-education.md) — Provides a comprehensive educational curriculum and reference implementations for learning deep learning with TensorFlow.
- [AI Development Guides](https://awesome-repositories.com/f/education-learning-resources/ai-development-guides.md) — Serves as a practical implementation guide for developing generative models, autoencoders, and RL agents.
- [Machine Learning Curricula](https://awesome-repositories.com/f/education-learning-resources/curriculum-structures/machine-learning-curricula.md) — Offers a structured curriculum covering gradient descent, model optimization, and data preprocessing.
- [Deep Learning Tutorials](https://awesome-repositories.com/f/education-learning-resources/deep-learning-tutorials.md) — Provides step-by-step instructional resources for building various neural network architectures.

### Scientific & Mathematical Computing

- [Graph-Based Computational Execution](https://awesome-repositories.com/f/scientific-mathematical-computing/data-modeling-processing/computational-graphs/graph-based-computational-execution.md) — Enables the execution of directed acyclic graphs to perform automatic differentiation and compute network results. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/session))
- [Tensor Manipulations](https://awesome-repositories.com/f/scientific-mathematical-computing/tensor-manipulations.md) — Handles multi-dimensional tensors to facilitate numerical processing across different data dimensions. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/structure))
- [Dimensionality Reduction](https://awesome-repositories.com/f/scientific-mathematical-computing/dimensionality-reduction.md) — Implements mathematical techniques to reduce high-dimensional data into lower-dimensional representations. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/intro-autoencoder))
- [Mean Squared Error Scorers](https://awesome-repositories.com/f/scientific-mathematical-computing/ordinary-least-squares/mean-squared-error-scorers.md) — Computes the average squared difference between predicted values and actual targets to evaluate regression models. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/example2))

### Part of an Awesome List

- [Model Optimization](https://awesome-repositories.com/f/awesome-lists/ai/model-optimization.md) — Demonstrates regularization, dropout, and advanced optimizers to improve convergence and prevent overfitting.
- [Data Analysis and Visualization](https://awesome-repositories.com/f/awesome-lists/data/data-analysis-and-visualization.md) — Provides tools for cleaning datasets and generating visual representations to analyze data patterns. ([source](https://mofanpy.com/))

### Data & Databases

- [ML Batch Training Optimizations](https://awesome-repositories.com/f/data-databases/batch-processing/ml-batch-training-optimizations.md) — Implements stochastic gradient descent batching to manage computational load during neural network training. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/classifier))
- [Spatial Pooling](https://awesome-repositories.com/f/data-databases/data-reducers/spatial-pooling.md) — Reduces the spatial dimensions of feature maps using max or average pooling to decrease computational complexity. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/CNN2))

### System Administration & Monitoring

- [Training Metric Monitors](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/observability-platforms/metric-performance-monitors/training-metric-monitors.md) — Tracks critical machine learning performance indicators such as loss and accuracy using dashboarding tools. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/))

### Testing & Quality Assurance

- [Classification Accuracy Scorers](https://awesome-repositories.com/f/testing-quality-assurance/model-evaluation-benchmarks/correction-accuracy-evaluators/classification-accuracy-scorers.md) — Measures the proportion of correctly classified instances to evaluate the predictive performance of classification models. ([source](https://mofanpy.com/tutorials/machine-learning/tensorflow/classifier))