[英]How to convert UnsafeMutablePointer<UInt8> to UIImage in Swift
[英]CoreGraphics - Can't replace UnsafeMutablePointer<UInt32> with UnsafeMutablePointer<UInt8>
我刚刚开始搞乱图像处理,遇到了两个非常奇怪的问题,或者至少我认为是。 我以为我犯了一些非常愚蠢的错误。
我打算对此发布另一个问题,但是,有时使用下面的代码,我还会得到随机噪声,而不是用户绘制数字的像素表示。 如果有人能告诉我为什么也会发生这种情况,我将不胜感激。 我很难找出原因,因为我阅读的所有内容都表明该代码应该可以工作。
如果有人需要更多信息,请告诉我! 提前谢谢你的帮助!
目标:
首先,获取用户在屏幕上绘制的数字。 然后,将图像的大小调整为28 x28。接下来,将图像转换为灰度并获得归一化像素值的数组。 最后,将标准化的灰度像素值输入到机器学习算法中。
[注意:在下面的图片中,点表示0值,而1s表示值>0。]
下面代码的输出效果很好。 如果用户画一个“ 3”,我通常会得到以下内容:
问题:
如果我将UnsafeMutablePointer和Buffer的大小更改为UInt8,则会得到随机噪声。 或者,如果我用[UInt32](repeating: 0, count: totalBytes)
或什至[UInt8](repeating: 0, count: totalBytes)
替换UnsafeMutablePointer和Buffer,则每个像素最终都为0,我真的不明白。
如果将UnsafeMutablePointer和Buffer的大小更改为UInt8,这是像素的输出:
获取灰度像素的代码:
public extension UIImage
{
private func grayScalePixels() -> UnsafeMutableBufferPointer<UInt32>?
{
guard let cgImage = self.cgImage else { return nil }
let bitsPerComponent = 8
let width = cgImage.width
let height = cgImage.height
let totalBytes = (width * height)
let colorSpace = CGColorSpaceCreateDeviceGray()
let data = UnsafeMutablePointer<UInt32>.allocate(capacity: totalBytes)
defer { data.deallocate(capacity: totalBytes) }
guard let imageContext = CGContext(data: data, width: width, height: height, bitsPerComponent: bitsPerComponent, bytesPerRow: width, space: colorSpace, bitmapInfo: 0) else { return nil }
imageContext.draw(cgImage, in: CGRect(origin: CGPoint.zero, size: CGSize(width: width, height: height)))
return UnsafeMutableBufferPointer<UInt32>(start: data, count: totalBytes)
}
public func normalizedGrayScalePixels() -> [CGFloat]?
{
guard let cgImage = self.cgImage else { return nil }
guard let pixels = self.grayScalePixels() else { return nil }
let width = cgImage.width
let height = cgImage.height
var result = [CGFloat]()
for y in 0..<height
{
for x in 0..<width
{
let index = ((width * y) + x)
let pixel = (CGFloat(pixels[index]) / 255.0)
result.append(pixel)
}
}
return result
}
}
绘制号码的代码:
func drawLineFrom(fromPoint: CGPoint, toPoint: CGPoint)
{
UIGraphicsBeginImageContextWithOptions(self.view.bounds.size, false, 1)
self.tempImageView.image?.draw(at: CGPoint.zero)
let context = UIGraphicsGetCurrentContext()
context?.move(to: fromPoint)
context?.addLine(to: toPoint)
context?.setLineCap(.round)
context?.setLineWidth(self.brushWidth)
context?.setStrokeColor(gray: 0, alpha: 1)
context?.strokePath()
self.tempImageView.image = UIGraphicsGetImageFromCurrentImageContext()
self.tempImageView.alpha = self.opacity
UIGraphicsEndImageContext()
}
override func touchesBegan(_ touches: Set<UITouch>, with event: UIEvent?)
{
self.swiped = false
if let touch = touches.first {
self.lastPoint = touch.location(in: self.view)
}
}
override func touchesMoved(_ touches: Set<UITouch>, with event: UIEvent?)
{
self.swiped = true
if let touch = touches.first
{
let currentPoint = touch.location(in: self.view)
self.drawLineFrom(fromPoint: self.lastPoint, toPoint: currentPoint)
self.lastPoint = currentPoint
}
}
override func touchesEnded(_ touches: Set<UITouch>, with event: UIEvent?)
{
if !swiped {
self.drawLineFrom(fromPoint: self.lastPoint, toPoint: self.lastPoint)
}
self.predictionLabel.text = "Predication: \(self.predict())"
self.tempImageView.image = nil
}
预测号码的代码:
private func printNumber(rowSize: Int, inputs: Vector)
{
for (index, pixel) in inputs.enumerated()
{
if index % rowSize == 0 { print() }
if (pixel > 0) {
print("1", terminator: " ")
}
else { print(".", terminator: " ") }
}
print()
}
private func predict() -> Scalar
{
let resizedImaege = self.tempImageView.image!.resizedImage(CGSize(width: 28, height: 28), interpolationQuality: .high)
let inputs = resizedImaege!.normalizedGrayScalePixels()!.flatMap({ Scalar($0) })
self.feedforwardResult = self.neuralNetwork!.feedForward(inputs: inputs)
self.printNumber(rowSize: 28, inputs: inputs)
let max = self.feedforwardResult!.activations.last!.max()!
let prediction = self.feedforwardResult!.activations.last!.index(of: max)!
return Scalar(prediction)
}
这行代码中最糟糕的一件事是该行:
defer { data.deallocate(capacity: totalBytes) }
data.deallocate(capacity: totalBytes)
仅在退出方法grayScalePixels()
之前执行。 因此, baseAddress
返回的UnsafeMutableBufferPointer
指向一个已释放的区域,这意味着你不能指望任何预见的结果,当访问该地区。
如果要使用UnsafeMutableBufferPointer
,则需要在完成对该区域的所有访问之后(在下面的代码中排名1),然后重新分配该区域:
private func grayScalePixels() -> UnsafeMutableBufferPointer<UInt8>? {
guard let cgImage = self.cgImage else { return nil }
let bitsPerComponent = 8
let width = cgImage.width
let height = cgImage.height
let totalBytes = width * height
let colorSpace = CGColorSpaceCreateDeviceGray()
let data = UnsafeMutablePointer<UInt8>.allocate(capacity: totalBytes)
data.initialize(to: UInt8.max, count: totalBytes) //<- #4
guard let imageContext = CGContext(data: data, width: width, height: height, bitsPerComponent: bitsPerComponent, bytesPerRow: width, space: colorSpace, bitmapInfo: 0) else { return nil }
imageContext.draw(cgImage, in: CGRect(x: 0, y: 0, width: width, height: height))
return UnsafeMutableBufferPointer(start: data, count: totalBytes)
}
public func normalizedGrayScalePixels() -> [CGFloat]? {
guard let cgImage = self.cgImage else { return nil }
guard let pixels = self.grayScalePixels() else { return nil }
let width = cgImage.width
let height = cgImage.height
var result: [CGFloat] = []
for y in 0..<height {
for x in 0..<width {
let index = width * y + x
let pixel = CGFloat(pixels[index]) / CGFloat(UInt8.max)
result.append(pixel)
}
}
pixels.baseAddress!.deinitialize(count: pixels.count) //<- #2
pixels.baseAddress!.deallocate(capacity: pixels.count) //<- #1
return result
}
(#2) deinitialize
可以不需要用于UInt8
在当前实现中夫特,但序列:分配-初始化- deinitilize - DEALLOCATE是推荐的方式。
(我碰到的其他几行只是我的偏好,并不重要。)
否则,如果您想使用Swift Array
而不是UnsafeMutableBufferPointer
,则可以编写如下代码:
private func grayScalePixels() -> [UInt8]? {
guard let cgImage = self.cgImage else { return nil }
let bitsPerComponent = 8
let width = cgImage.width
let height = cgImage.height
let totalBytes = width * height
let colorSpace = CGColorSpaceCreateDeviceGray()
var byteArray: [UInt8] = Array(repeating: UInt8.max, count: totalBytes) //<- #4
let success = byteArray.withUnsafeMutableBufferPointer {(buffer)->Bool in
guard let imageContext = CGContext(data: buffer.baseAddress!, width: width, height: height, bitsPerComponent: bitsPerComponent, bytesPerRow: width, space: colorSpace, bitmapInfo: 0) else { return false }
imageContext.draw(cgImage, in: CGRect(x: 0, y: 0, width: width, height: height))
return true;
}
return success ? byteArray : nil
}
public func normalizedGrayScalePixels() -> [CGFloat]? {
guard let cgImage = self.cgImage else { return nil }
guard let pixels = self.grayScalePixels() else { return nil }
let width = cgImage.width
let height = cgImage.height
var result: [CGFloat] = []
for y in 0..<height {
for x in 0..<width {
let index = width * y + x
let pixel = CGFloat(pixels[index]) / CGFloat(UInt8.max)
result.append(pixel)
}
}
return result
}
您可能需要修改上面的代码以使其与您的代码一起使用,因为我无法使用UInt32
版本的grayScalePixels()
复制相同的结果。
我在代码中发现了一个问题。 您的绘图代码使用以下内容绘制线条:
context?.setStrokeColor(gray: 0, alpha: 1)
灰度等级0,黑色。 在旧代码中,我将位图初始化为:
data.initialize(to: 0, count: totalBytes)
要么:
var byteArray: [UInt8] = Array(repeating: 0, count: totalBytes)
因此,在黑色上绘制黑色,结果是:全黑,8位灰度级,全0。 (我最初写的initialize
可能不需要,但这是一个错误。带有alpha的图像将与初始位图内容混合绘制。)
我更新后的代码(标记为#4
)用白色初始化位图(以8位灰度表示, 255
== 0xFF
== UInt8.max
)。
并且最好通过更新printNumber(rowSize:inputs:)
检测非白色像素:
private func printNumber(rowSize: Int, inputs: Vector) {
for (index, pixel) in inputs.enumerated() {
if index % rowSize == 0 { print() }
if pixel < 1.0 { //<- #4
print("1", terminator: "")
}
else { print(".", terminator: "") }
}
print()
}
在归一化的灰度浮点数中, 1.0
是白色的值,最好将非白色显示为1
。 (或者,找到另一个更好的阈值。)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.