[英]How to convert TF_Tensor to opencv Mat in C++?
I am trying to port Python Tensorflow model to C++.我正在尝试将 Python Tensorflow model 移植到 ZF6F87C9FDCF8B3C3F07F93F1EE8。 In process, I need to convert the TF_Tensor class to cv::Mat.在此过程中,我需要将 TF_Tensor class 转换为 cv::Mat。
I created the output tensor as the below.我创建了 output 张量,如下所示。
TF_Tensor** OutputValues = (TF_Tensor**)malloc(sizeof(TF_Tensor*) * NumOutputs);
Then I loaded model and the session was completed successfully, but I failed to convert OutputValues to cv::Mat.然后我加载了 model 和 session 成功完成,但我未能将 OutputValues 转换为 cv::Mat。
I obtained a pointer to the data buffer by the code below.我通过下面的代码获得了指向数据缓冲区的指针。
const float* camBuf = (float*)TF_TensorData(*OutputValues);
But when I tried to create cv::Mat by the code below,但是当我尝试通过下面的代码创建 cv::Mat 时,
cv::Mat testInputImage(
80,
80,
3,
TF_TensorData(*OutputValues)
);
Image is not generated correctly.图像未正确生成。
I could not find any reference to TF_Tensor data structure, so I am asking for a help.我找不到任何对 TF_Tensor 数据结构的引用,所以我寻求帮助。
try :
cv::Mat mat(width, height, CV_32F);
std::memcpy((void *)mat.data, camBuf , sizeof(TF_Tensor*) * NumOutputs);
By doing:通过做:
cv::Mat testInputImage(80, 80, CV_32FC(3), TF_TensorData(*OutputValues));
you are "wrapping" the existing data in a cv::Mat
, which avoids a copy.您正在将现有数据“包装”在cv::Mat
中,从而避免复制。 Note that the third argument should be CV_32FC(3)
(a 32-bit floating point image, with 3 channels).请注意,第三个参数应该是CV_32FC(3)
(32 位浮点图像,具有 3 个通道)。 This approach should work if OutputValues
is a TF_Tensor**
type, and if the underlying TF_Tensor
holds appropriate data.如果OutputValues
是TF_Tensor**
类型,并且基础TF_Tensor
包含适当的数据,则此方法应该有效。
However, I don't think that this:但是,我不认为这是:
TF_Tensor** OutputValues = (TF_Tensor**)malloc(sizeof(TF_Tensor*) * NumOutputs);
is an appropriate way to allocate a TF_Tensor;是分配 TF_Tensor 的合适方式; I think you should be using TF_AllocateTensor instead.我认为您应该改用TF_AllocateTensor 。
All that said, if you are using C++, you might consider using tf::Tensor API instead of TF_Tensor
(which is used for C, and is less common).综上所述,如果您使用的是 C++,您可以考虑使用tf::Tensor API 而不是TF_Tensor
(用于 Z0D61F8370CAD1D412F80B84D143E1257,不太常见)。
You omitted some details, but let's say your tensor is 4-dimensional (as is common), has float32 values, and is laid out as NxHxWxC (In other words, the tensor is holding a collection of float images).您省略了一些细节,但假设您的张量是 4 维的(很常见),具有 float32 值,并且布局为 NxHxWxC(换句话说,张量包含一组浮动图像)。 If you want to convert idx
-th element in the batch to a cv::Mat
, you can do it like this:如果要将批处理中的idx
元素转换为cv::Mat
,可以这样做:
tf::Tensor tensor = /* tensor from somewhere */;
int idx = /* index of the image in the batch */;
int batch_size = tensor.dim_size(0);
int rows = tensor.dim_size(1);
int cols = tensor.dim_size(2);
int channels = tensor.dim_size(3);
int row_size = channels * cols * sizeof(float);
cv::Mat image(rows, cols, CV_32FC(channels));
auto tensor_mapped = tensor.tensor<float, 4>();
for (int r = 0; r < rows; ++r) {
float* row = reinterpret_cast<float*>(mat.data + r * row_size);
for (int c = 0; c < cols; ++c) {
for (int k = 0; k < channels; ++k) {
row[k + c * channels] = tensor_mapped(idx, r, c, k);
}
}
}
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.