Cascade supports MLOps workflows for smaller projects without a full platform.
Open source
24 alternativestfdeploy
tfdeploy evaluates TensorFlow graphs and exports them to run with NumPy in environments without TensorFlow.
About tfdeploy
tfdeploy is an open-source Python project that converts TensorFlow graphs into a model file that can be loaded and evaluated with NumPy. It is intended for running trained TensorFlow models in environments where TensorFlow cannot be installed or run. According to the project, its evaluation is faster than TensorFlow's Tensor.eval, and it does not need TensorFlow during evaluation. TensorFlow is still required when creating a model.
The project states that it is no longer actively maintained. The author notes that the NumPy-based operations once had full feature parity with TensorFlow but could not keep up with TensorFlow's development. The code remains available as a readable reference implementation for many TensorFlow kernels. The project does not support GPUs.
Key features
- Converts a TensorFlow graph into a model file that can be saved and reloaded
- Evaluates models with NumPy using named input and output tensors
- Loads one or more models from a single file
- Core implementation of fewer than 150 lines in a single file that can be copied into a project
- Supports custom operations by defining a class that inherits from tfdeploy.Operation
Best for: Developers who need to run a trained TensorFlow model with NumPy in an environment without TensorFlow, or who want a short reference for how TensorFlow operations are implemented.
Good for
- Lightweight: the core is a single short file that depends only on NumPy
- Does not need TensorFlow during model evaluation
- Custom operations can be added for operations it does not yet implement
Watch out for
- No longer actively maintained, so newer TensorFlow operations may be missing
- TensorFlow is required to create a model
- Does not support GPUs
tfdeploy at a glance
- Website
- github.com/riga/tfdeploy
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
tfdeploy alternatives
Tools and sites you could use instead, ranked by how closely they match.
Gymnasium provides a standard API for single agent reinforcement learning environments and related utilities.
Open source
24 alternatives
QKeras provides quantization tools for deep learning with TensorFlow Keras.
Open source
24 alternatives
Tensorforce provides a TensorFlow library for applied reinforcement learning tasks.
Open source
24 alternatives
einops provides readable tensor operations for PyTorch, JAX, TensorFlow, and other frameworks.
Open source
24 alternatives
PyTorch Ignite provides a high level library for flexibly training and evaluating neural networks.
Open source
24 alternativesPopular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioCoreWeavecoreweave.comKili Technologykili-technology.comAPI docsdocs.x.ai
tfdeploy FAQ
Does tfdeploy need TensorFlow to run a saved model?
No. The project states that TensorFlow is not needed during evaluation. TensorFlow is required when creating a model from a graph.
Does tfdeploy support GPUs?
No. The project states that it does not support GPUs.
Is tfdeploy still maintained?
The project states that it is no longer actively maintained. The code remains available as a reference implementation.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.