TensorSwift 0.2.2

TensorSwift 0.2.2

×

测试已测试✓
语言语言 SwiftSwift
许可协议 MIT
发布上次发布2016年11月
SwiftSwift 版本3.0
SPM支持 SPM✓

由 Araki Takehiro 和 Koshizawa Yuta 维护。

TensorSwift 0.2.2

  • 由
  • Koshizawa Yuta 和 Araki Takehiro 提供

TensorSwift

TensorSwift 是一个轻量级库，用于计算张量，它具有与 TensorFlow 相似的 API。使用 TensorFlow 生成的模型，在 Swift 中模拟计算张量非常有用。

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)

高级 MNIST 深度学习教程

deep-mnist.gif

以下代码展示了如何使用 TensorSwift 模拟 高级 MNIST 深度学习教程，这是 TensorFlow 的一个教程。

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, 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
    }
}

安装

Swift 包管理器

.Package(url: "[email protected]:qoncept/TensorSwift.git", majorVersion: 0, minor: 2),

许可协议

MIT 许可协议