Skip to content


Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?


Hyperparameter Optimization for Keras, TensorFlow (tf.keras) and PyTorch

Talos Travis Talos Coveralls

TalosKey FeaturesExamplesInstallSupportDocsIssuesLicenseDownload

Talos radically changes the ordinary Keras, TensorFlow (tf.keras), and PyTorch workflow by fully automating hyperparameter tuning and model evaluation. Talos exposes Keras and TensorFlow (tf.keras) and PyTorch functionality entirely and there is no new syntax or templates to learn.



Talos radically transforms ordinary Keras, TensorFlow (tf.keras), and PyTorch workflows without taking away.

  • works with ANY Keras, TensorFlow (tf.keras) or PyTorch model
  • takes minutes to implement
  • no new syntax to learn
  • adds zero new overhead to your workflow

Talos is made for data scientists and data engineers that want to remain in complete control of their TensorFlow (tf.keras) and PyTorch models, but are tired of mindless parameter hopping and confusing optimization solutions that add complexity instead of reducing it. Within minutes, without learning any new syntax, Talos allows you to configure, perform, and evaluate hyperparameter optimization experiments that yield state-of-the-art results across a wide range of prediction tasks. Talos provides the simplest and yet most powerful available method for hyperparameter optimization with TensorFlow (tf.keras) and PyTorch.

🔧 Key Features

Based on what no doubt constitutes a "biased" review (being our own) of more than ~30 hyperparameter tuning and optimization solutions, Talos comes on top in terms of intuitive, easy-to-learn, highly permissive access to critical hyperparameter optimization capabilities. Key features include:

  • Single-line optimize-to-predict pipeline talos.Scan(x, y, model, params).predict(x_test, y_test)
  • Automated hyperparameter optimization
  • Model generalization evaluator
  • Experiment analytics
  • Pseudo, Quasi, and Quantum Random search options
  • Grid search
  • Probabilistic optimizers
  • Single file custom optimization strategies
  • Dynamically change optimization strategy during experiment
  • Support for man-machine cooperative optimization strategy
  • Model candidate generality evaluation
  • Live training monitor
  • Experiment analytics

Talos works on Linux, Mac OSX, and Windows systems and can be operated cpu, gpu, and multi-gpu systems.

▶️ Examples

Get the below code here. More examples further below.

The Simple example below is more than enough for starting to use Talos with any Keras model. Field Report has +2,600 claps on Medium because it's more entertaining.

Simple [1-2 mins]

Concise [~5 mins]

Comprehensive [~10 mins]

Field Report [~15 mins]

For more information on how Talos can help with your Keras, TensorFlow (tf.keras) and PyTorch workflow, visit the User Manual.

You may also want to check out a visualization of the Talos Hyperparameter Tuning workflow.

💾 Install

Stable version:

pip install talos

Daily development version:

pip install git+

💬 How to get Support

I want to... Go to...
...troubleshoot Docs · Wiki · GitHub Issue Tracker a bug GitHub Issue Tracker
...suggest a new feature GitHub Issue Tracker
...get support Stack Overflow

📢 Citations

If you use Talos for published work, please cite:

Autonomio Talos [Computer software]. (2020). Retrieved from

📃 License

MIT License