Haskell bindings for TensorFlow
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
jcmartin 6b19e54722
Update to haddock files for tensorflow-0.3 package (TensorFlow 2.3.0). (#269)
2 weeks ago
ci_build Tensorflow 2.3.0 Support (#267) 3 weeks ago
docker Tensorflow 2.3.0 Support (#267) 3 weeks ago
docs/haddock Update to haddock files for tensorflow-0.3 package (TensorFlow 2.3.0). (#269) 2 weeks ago
nix nix-shell updated to be compatible with LTS14.4 (#254) 9 months ago
tensorflow Update Package Version Numbers (#268) 2 weeks ago
tensorflow-core-ops Update Package Version Numbers (#268) 2 weeks ago
tensorflow-logging Update Package Version Numbers (#268) 2 weeks ago
tensorflow-mnist Update Package Version Numbers (#268) 2 weeks ago
tensorflow-mnist-input-data Modifying tensorflow-mnist-input-data's setup to download MNIST through http proxy if necessary (#127) 3 years ago
tensorflow-opgen Update Package Version Numbers (#268) 2 weeks ago
tensorflow-ops Update Package Version Numbers (#268) 2 weeks ago
tensorflow-proto Update Package Version Numbers (#268) 2 weeks ago
tensorflow-records Update to current proto-lens packages. (#258) 6 months ago
tensorflow-records-conduit Update to LTS-11 (#187) 2 years ago
tensorflow-test Fix .cabal files so 'stack check' passes. (#110) 3 years ago
third_party Tensorflow 2.3.0 Support (#267) 3 weeks ago
tools Upgrade to tensorflow 1.14.0 (#244) 1 year ago
.gitignore Tensorflow 2.3.0 Support (#267) 3 weeks ago
.gitmodules Initial commit 4 years ago
CONTRIBUTING.md Initial commit 4 years ago
ChangeLog.md Switch to LTS 14 and bump versions to 0.2.0.1 (#248) 1 year ago
LICENSE Initial commit 4 years ago
README.md Update to haddock files for tensorflow-0.3 package (TensorFlow 2.3.0). (#269) 2 weeks ago
shell.nix nix-shell updated to be compatible with LTS14.4 (#254) 9 months ago
stack.yaml Tensorflow 2.3.0 Support (#267) 3 weeks ago

README.md

Build Status

The tensorflow-haskell package provides Haskell bindings to TensorFlow.

This is not an official Google product.

Documentation

https://tensorflow.github.io/haskell/haddock/

TensorFlow.Core is a good place to start.

Examples

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 (TF.run trainStep)
    -- Return the learned parameters.
    (TF.Scalar w', TF.Scalar b') <- TF.run (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 https://github.com/tensorflow/haskell.git tensorflow-haskell
cd tensorflow-haskell
IMAGE_NAME=tensorflow/haskell:v0
docker build -t $IMAGE_NAME docker
# TODO: move the setup step to the docker script.
stack --docker --docker-image=$IMAGE_NAME setup
stack --docker --docker-image=$IMAGE_NAME test

There is also a demo application:

cd tensorflow-mnist
stack --docker --docker-image=$IMAGE_NAME build --exec Main

Stack + Docker + GPU

If you want to use GPU you can do:

IMAGE_NAME=tensorflow/haskell:2.3.0-gpu
docker build -t $IMAGE_NAME docker/gpu

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/nvidia-docker-wrapper.sh <somewhere in your path>/docker
stack --docker --docker-image=$IMAGE_NAME setup
stack --docker --docker-image=$IMAGE_NAME test

Build on macOS

Run the install_macos_dependencies.sh 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 shell.nix provides an environment containing the necessary dependencies. To build, run:

$ stack --nix build

or alternatively you can run

$ nix-shell

to enter the environment and build the project. Note, that it is an emulation of common Linux environment rather than full-featured Nix package expression. No exportable Nix package will appear, but local development is possible.

Installation on CentOS

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

Related Projects

Statically validated tensor shapes

https://github.com/helq/tensorflow-haskell-deptyped is experimenting with using dependent types to statically validate tensor shapes. May be merged with this repository in the future.

Example:

{-# 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

License

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