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?


Failed to load latest commit information.
Latest commit message
Commit time
January 23, 2023 17:17
January 23, 2023 17:17
March 4, 2023 21:48
October 24, 2016 19:26
October 24, 2016 19:26
October 24, 2016 19:26

Build Status

The tensorflow-haskell package provides Haskell bindings to TensorFlow.

This is not an official Google product.


TensorFlow.Core is a good place to start.


Neural network model for the MNIST dataset: code

Toy example of a linear regression model (full code):

import Control.Monad (replicateM, replicateM_)
import System.Random (randomIO)
import Test.HUnit (assertBool)

import qualified TensorFlow.Core as TF
import qualified TensorFlow.GenOps.Core as TF
import qualified TensorFlow.Minimize as TF
import qualified TensorFlow.Ops as TF hiding (initializedVariable)
import qualified TensorFlow.Variable as TF

main :: IO ()
main = do
    -- Generate data where `y = x*3 + 8`.
    xData <- replicateM 100 randomIO
    let yData = [x*3 + 8 | x <- xData]
    -- Fit linear regression model.
    (w, b) <- fit xData yData
    assertBool "w == 3" (abs (3 - w) < 0.001)
    assertBool "b == 8" (abs (8 - b) < 0.001)

fit :: [Float] -> [Float] -> IO (Float, Float)
fit xData yData = TF.runSession $ do
    -- Create tensorflow constants for x and y.
    let x = TF.vector xData
        y = TF.vector yData
    -- Create scalar variables for slope and intercept.
    w <- TF.initializedVariable 0
    b <- TF.initializedVariable 0
    -- Define the loss function.
    let yHat = (x `TF.mul` TF.readValue w) `TF.add` TF.readValue b
        loss = TF.square (yHat `TF.sub` y)
    -- Optimize with gradient descent.
    trainStep <- TF.minimizeWith (TF.gradientDescent 0.001) loss [w, b]
    replicateM_ 1000 ( trainStep)
    -- Return the learned parameters.
    (TF.Scalar w', TF.Scalar b') <- (TF.readValue w, TF.readValue b)
    return (w', b')

Installation Instructions

Note: building this repository with stack requires version 2.3.1 or newer. Check your stack version with stack --version in a terminal.

Build with Docker on Linux

As an expedient we use docker for building. Once you have docker working, the following commands will compile and run the tests.

git clone --recursive tensorflow-haskell
cd tensorflow-haskell
docker build -t tensorflow/haskell:2.10.1 docker
# TODO: move the setup step to the docker script.
stack --docker setup
stack --docker test

There is also a demo application:

cd tensorflow-mnist
stack --docker build --exec Main

Stack + Docker + GPU

If you want to use GPU you can do:

docker build -t $IMAGE_NAME docker/gpu
# TODO: move the setup step to the docker script.
stack --docker --docker-image=$IMAGE_NAME setup
stack --docker --docker-image=$IMAGE_NAME test

Using nvidia-docker version 2

See Nvidia docker 2 install instructions

stack --docker --docker-image=$IMAGE_NAME setup
stack --docker --docker-run-args "--runtime=nvidia" --docker-image=$IMAGE_NAME test

Using nvidia-docker classic

Stack needs to use nvidia-docker instead of the normal docker for GPU support. We must wrap 'docker' with a script. This script will shadow the normal docker command.

ln -s `pwd`/tools/ <somewhere in your path>/docker
stack --docker --docker-image=$IMAGE_NAME setup
stack --docker --docker-image=$IMAGE_NAME test

Build on macOS

Run the script in the tools/ directory. The script installs dependencies via Homebrew and then downloads and installs the TensorFlow library on your machine under /usr/local.

After running the script to install system dependencies, build the project with stack:

stack test

Build on NixOS

The stack.yaml file describes a NixOS environment containing the necessary dependencies. To build, run:

$ stack --nix build

Installation on CentOS

Xiaokui Shu (@subbyte) maintains separate instructions for installation on CentOS.

Related Projects

Statically validated tensor shapes is experimenting with using dependent types to statically validate tensor shapes. May be merged with this repository in the future.


{-# LANGUAGE DataKinds, ScopedTypeVariables #-}

import Data.Maybe (fromJust)
import Data.Vector.Sized (Vector, fromList)
import TensorFlow.DepTyped

test :: IO (Vector 8 Float)
test = runSession $ do
  (x :: Placeholder "x" '[4,3] Float) <- placeholder

  let elems1 = fromJust $ fromList [1,2,3,4,1,2]
      elems2 = fromJust $ fromList [5,6,7,8]
      (w :: Tensor '[3,2] '[] Build Float) = constant elems1
      (b :: Tensor '[4,1] '[] Build Float) = constant elems2
      y = (x `matMul` w) `add` b -- y shape: [4,2] (b shape is [4.1] but `add` broadcasts it to [4,2])

  let (inputX :: TensorData "x" [4,3] Float) =
          encodeTensorData . fromJust $ fromList [1,2,3,4,1,0,7,9,5,3,5,4]

  runWithFeeds (feed x inputX :~~ NilFeedList) y

main :: IO ()
main = test >>= print


This project is licensed under the terms of the Apache 2.0 license.