Ios 如何在MPSNNGRAPHER的输入端使用两个MPS图像

我试图在MPSNNGraph上输入两幅图像

然而，即使我在“withSourceImages”上输入类似[input1，input2]的数组，我也只能输入“input1”作为输入图像。理想情况下，在创建下图时，我希望将“inputImage1”设置为“input1”，将“inputImage2”设置为“input2”

事实上，当我像这样运行它并查看“concat”的结果时，我能够看到连接的是什么“input1”，而不是“input2”

图表如下所示：

let inputImage1 = MPSNNImageNode(handle: nil)
let inputImage2 = MPSNNImageNode(handle: nil)
let scale = MPSNNBilinearScaleNode(source: inputImage1,
                                   outputSize: MTLSize(width:256,
                                                       height: 256,
                                                       depth: 3))
let scale2 = MPSNNBilinearScaleNode(source: inputImage1,
                                   outputSize: MTLSize(width:64,
                                                       height: 64,
                                                       depth: 3))
...

let concat = MPSNNConcatenationNode(sources: [conv3.resultImage, scale2.resultImage])

...

if let graph = MPSNNGraph(device: commandQueue.device,
                          resultImage: tanh.resultImage,
                          resultImageIsNeeded: true){
        self.graph = graph
}

let input1 = MPSImage(texture: texture, ...)
let input2 = MPSImage(texture: texture2, ...)
graph.executeAsync(withSourceImages: [input1, input2]) { outputImage, error in
    ...
}

编码图的一部分如下所示：

let inputImage1 = MPSNNImageNode(handle: nil)
let inputImage2 = MPSNNImageNode(handle: nil)
let scale = MPSNNBilinearScaleNode(source: inputImage1,
                                   outputSize: MTLSize(width:256,
                                                       height: 256,
                                                       depth: 3))
let scale2 = MPSNNBilinearScaleNode(source: inputImage1,
                                   outputSize: MTLSize(width:64,
                                                       height: 64,
                                                       depth: 3))
...

let concat = MPSNNConcatenationNode(sources: [conv3.resultImage, scale2.resultImage])

...

if let graph = MPSNNGraph(device: commandQueue.device,
                          resultImage: tanh.resultImage,
                          resultImageIsNeeded: true){
        self.graph = graph
}

let input1 = MPSImage(texture: texture, ...)
let input2 = MPSImage(texture: texture2, ...)
graph.executeAsync(withSourceImages: [input1, input2]) { outputImage, error in
    ...
}

如何输入第二个输入，图形如何接收

---

你能给我一些建议吗？

你提供的代码实际上看起来是正确的。此处引用MPSNNGraph.h标题：

*  @param  sourceImages    A list of MPSImages to use as the source images for the graph.
*                          These should be in the same order as the list returned from
*                          MPSNNGraph.sourceImageHandles. They should be allocated against
*                          the same MTLDevice. There must be at least one source image.
*                          Note: this array is intended to handle the case where multiple
*                          input images are required to generate a single graph result.
*                          That is, the graph itself has multiple inputs.  If you need to
*                          execute the graph multiple times, then call this API multiple
*                          times, or better yet use [encodeToCommandBuffer:sourceImages:]
*                          multiple times.

---

不过我想指出，MPSNNConcatenationNode的行为方式非常独特。它始终与深度（通道）尺寸有关。当用不同的空间尺寸浓缩图像时，它将尊重较小的图像（即2x2x10浓缩4x4x15->2x2x25）。可能这就是问题的来源。

Scale2使用与本例中Scale1相同的输入图像。当MPSNNGraph分析这组节点时，它从未遇到inputImage2，因为它不被图使用。因为它不在图形中，所以图形接口将不接受第二个输入。它不知道该怎么办

在我看来，如果您将scale2初始化更改为使用inputImage2，那么它将按照您的预期工作