https://github.com/qoncept/TensorSwift

A lightweight library to calculate tensors in Swift, which has similar APIs to TensorFlow's
https://github.com/qoncept/TensorSwift

Last synced: 6 days ago
JSON representation

A lightweight library to calculate tensors in Swift, which has similar APIs to TensorFlow's

• Host: GitHub
• URL: https://github.com/qoncept/TensorSwift
• Owner: qoncept
• License: mit
• Created: 2016-03-11T09:50:51.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2017-10-24T09:02:48.000Z (about 7 years ago)
• Last Synced: 2024-04-24T19:01:47.647Z (8 months ago)
• Language: Swift
• Homepage:
• Size: 13.7 MB
• Stars: 322
• Watchers: 22
• Forks: 21
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-ios - TensorSwift - A lightweight library to calculate tensors in Swift, which has similar APIs to TensorFlow's. (Machine Learning / Other Hardware)
• awesome-machine-learning - TensorSwift
• awesome-ios-star - TensorSwift - A lightweight library to calculate tensors in Swift, which has similar APIs to TensorFlow's. (Machine Learning / Other Hardware)

README

        
# TensorSwift

_TensorSwift_ is a lightweight library to calculate tensors, which has similar APIs to [_TensorFlow_](https://www.tensorflow.org/)'s. _TensorSwift_ is useful to simulate calculating tensors in Swift **using models trained by _TensorFlow_**.

```swift

let a = Tensor(shape: [2, 3], elements: [1, 2, 3, 4, 5, 6])

let b = Tensor(shape: [2, 3], elements: [7, 8, 9, 10, 11, 12])

let sum = a + b // Tensor(shape: [2, 3], elements: [8, 10, 12, 14, 16, 18])

let mul = a * b // Tensor(shape: [2, 3], elements: [7, 16, 27, 40, 55, 72])

let c = Tensor(shape: [3, 1], elements: [7, 8, 9])

let matmul = a.matmul(c) // Tensor(shape: [2, 1], elements: [50, 122])

let zeros = Tensor(shape: [2, 3, 4])

let ones = Tensor(shape: [2, 3, 4], element: 1)

```

## Deep MNIST for Experts

![deep-mnist.gif](Resources/DeepMnist.gif)

The following code shows how to simulate [Deep MNIST for Experts](https://www.tensorflow.org/versions/r0.8/tutorials/mnist/pros/index.html), a tutorial of _TensorFlow_, by _TensorSwift_.

```swift

public struct Classifier {

    public let W_conv1: Tensor

    public let b_conv1: Tensor

    public let W_conv2: Tensor

    public let b_conv2: Tensor

    public let W_fc1: Tensor

    public let b_fc1: Tensor

    public let W_fc2: Tensor

    public let b_fc2: Tensor

    

    public func classify(_ x_image: Tensor) -> Int {

        let h_conv1 = (x_image.conv2d(filter: W_conv1, strides: [1, 1, 1]) + b_conv1).relu()

        let h_pool1 = h_conv1.maxPool(kernelSize: [2, 2, 1], strides: [2, 2, 1])

        

        let h_conv2 = (h_pool1.conv2d(filter: W_conv2, strides: [1, 1, 1]) + b_conv2).relu()

        let h_pool2 = h_conv2.maxPool(kernelSize: [2, 2, 1], strides: [2, 2, 1])

        

        let h_pool2_flat = h_pool2.reshaped([1, Dimension(7 * 7 * 64)])

        let h_fc1 = (h_pool2_flat.matmul(W_fc1) + b_fc1).relu()

        

        let y_conv = (h_fc1.matmul(W_fc2) + b_fc2).softmax()

        return y_conv.elements.enumerated().max { $0.1 < $1.1 }!.0

    }

}

```

## Installation

### Swift Package Manager

```swift

.Package(url: "[email protected]:qoncept/TensorSwift.git", from: "0.2.0"),

```

### CocoaPods

```

pod 'TensorSwift', '~> 0.2'

```

### Carthage

```

github "qoncept/TensorSwift" ~> 0.2

```

## License

[The MIT License](LICENSE)