如何将 Byte[](解码为 PNG 或 JPG)转换为 Tensorflows Tensor [英] How to transform Byte[](decoded as PNG or JPG) to Tensorflows Tensor
问题描述
我正在尝试在 Unity 的项目中使用 Tensorflowsharp.
I'am trying to use Tensorflowsharp in a Project in Unity.
我面临的问题是,对于转换,您通常使用第二个 Graph 将输入转换为张量.Android 不支持使用的函数 DecodeJpg 和 DecodePng 那么如何将该输入转换为张量?
The problem i'm facing is that for the transform you usually use a second Graph to transform the input into a tensor. The used functions DecodeJpg and DecodePng are not supported on Android so how can you transform that input into a tensor ?
private static void ConstructGraphToNormalizeImage(out TFGraph graph, out TFOutput input, out TFOutput output, TFDataType destinationDataType = TFDataType.Float)
{
const int W = 224;
const int H = 224;
const float Mean = 117;
const float Scale = 1;
graph = new TFGraph();
input = graph.Placeholder(TFDataType.String);
output = graph.Cast(graph.Div(
x: graph.Sub(
x: graph.ResizeBilinear(
images: graph.ExpandDims(
input: graph.Cast(
graph.DecodeJpeg(contents: input, channels: 3), DstT: TFDataType.Float),
dim: graph.Const(0, "make_batch")),
size: graph.Const(new int[] { W, H }, "size")),
y: graph.Const(Mean, "mean")),
y: graph.Const(Scale, "scale")), destinationDataType);
}
其他解决方案似乎会产生不准确的结果.
Other solutions seem to create non accurate results.
也许以某种方式使用 Mat 对象?
Maybe somehow with a Mat object?
和我的我在 Unity 中的 c# 中实现了一些比较,它部分工作.它根本不准确.我要如何找出均值?我找不到有关 rgb 订单的任何信息.?我对此很陌生,所以也许我只是忽略了它.(在 Tensorflow.org 上)使用在 1.4 中训练的 MobileNet.
and my I implemented something comparabel in c# in Unity and it works partially. It is just not accurate at all. How am i gonna find out the Mean? And i could not find anything about the rgb order.? I'm really new to this so maybe i have just overlooked it. (on Tensorflow.org) Using MobileNet trained in 1.4.
public TFTensor transformInput(Color32[] pic, int texturewidth, int textureheight)
{
const int W = 224;
const int H = 224;
const float imageMean = 128;
const float imageStd = 128;
float[] floatValues = new float[texturewidth * textureheight * 3];
for (int i = 0; i < pic.Length; ++i)
{
var color = pic[i];
var index = i * 3;
floatValues[index] = (color.r - imageMean) / imageStd;
floatValues[index + 1] = (color.g - imageMean) / imageStd;
floatValues[index + 2] = (color.b - imageMean) / imageStd;
}
TFShape shape = new TFShape(1, W, H, 3);
return TFTensor.FromBuffer(shape, floatValues, 0, floatValues.Length);
}
推荐答案
你可以输入实际的浮点数组,而不是先输入字节数组然后使用 DecodeJpeg,你可以这样得到:
Instead of feeding the byte array and then use DecodeJpeg, you could feed the actual float array, which you can get like this:
float[] floatValues = new float[inputSize * inputSize * 3];
int[] intValues = new int[inputSize * inputSize];
bitmap.getPixels(intValues, 0, bitmap.getWidth(), 0, 0, bitmap.getWidth(), bitmap.getHeight());
for (int i = 0; i < intValues.length; ++i) {
final int val = intValues[i];
floatValues[i * 3 + 0] = (((val >> 16) & 0xFF) - imageMean) / imageStd;
floatValues[i * 3 + 1] = (((val >> 8) & 0xFF) - imageMean) / imageStd;
floatValues[i * 3 + 2] = ((val & 0xFF) - imageMean) / imageStd;
}
Tensor<Float> input = Tensors.create(floatValues);
要使用Tensors.create()",您至少需要 Tensorflow 1.4 版.
In order to use "Tensors.create()" you need to have at least Tensorflow version 1.4.
这篇关于如何将 Byte[](解码为 PNG 或 JPG)转换为 Tensorflows Tensor的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!