函数:Status ReadTensorFromImageFile(const string& file_name, const int input_height,
const int input_width, const float input_mean,
const float input_std,
std::vector<Tensor>* out_tensors)
函数作用:给定一个图像文件名,读入数据,尝试将其解码为图像,将其调整为所需大小,然后根据需要缩放。
函数声明情况如下:
函数声明文件如下:
函数流程图如下:
函数逻辑顺序图如下:
函数原始代码如下:
// Given an image file name, read in the data, try to decode it as an image,
// resize it to the requested size, and then scale the values as desired.
Status ReadTensorFromImageFile(const string& file_name, const int input_height,
const int input_width, const float input_mean,
const float input_std,
std::vector<Tensor>* out_tensors) {
auto root = tensorflow::Scope::NewRootScope();
using namespace ::tensorflow::ops; // NOLINT(build/namespaces)
string input_name = "file_reader";
string output_name = "normalized";
// read file_name into a tensor named input将文件名读入名为input的张量中。
Tensor input(tensorflow::DT_STRING, tensorflow::TensorShape());
TF_RETURN_IF_ERROR(
ReadEntireFile(tensorflow::Env::Default(), file_name, &input));
// use a placeholder to read input data使用占位符读取输入数据。
auto file_reader =
Placeholder(root.WithOpName("input"), tensorflow::DataType::DT_STRING);
std::vector<std::pair<string, tensorflow::Tensor>> inputs = {
{"input", input},
};
// Now try to figure out what kind of file it is and decode it.现在试着找出它是什么类型的文件并解码。
const int wanted_channels = 3;
tensorflow::Output image_reader;
if (tensorflow::str_util::EndsWith(file_name, ".png")) {
image_reader = DecodePng(root.WithOpName("png_reader"), file_reader,
DecodePng::Channels(wanted_channels));
} else if (tensorflow::str_util::EndsWith(file_name, ".gif")) {
// gif decoder returns 4-D tensor, remove the first dimgif解码器返回4-D张量,移除第一个dim。
image_reader =
Squeeze(root.WithOpName("squeeze_first_dim"),
DecodeGif(root.WithOpName("gif_reader"), file_reader));
} else if (tensorflow::str_util::EndsWith(file_name, ".bmp")) {
image_reader = DecodeBmp(root.WithOpName("bmp_reader"), file_reader);
} else {
// Assume if it's neither a PNG nor a GIF then it must be a JPEG.假设它既不是PNG也不是GIF,那么它必须是JPEG。
image_reader = DecodeJpeg(root.WithOpName("jpeg_reader"), file_reader,
DecodeJpeg::Channels(wanted_channels));
}
// Now cast the image data to float so we can do normal math on it.现在将图像数据转换为浮动,这样我们就可以对其进行正常的数学运算。
auto float_caster =
Cast(root.WithOpName("float_caster"), image_reader, tensorflow::DT_FLOAT);
// The convention for image ops in TensorFlow is that all images are expected
// to be in batches, so that they're four-dimensional arrays with indices of
// [batch, height, width, channel]. Because we only have a single image, we
// have to add a batch dimension of 1 to the start with ExpandDims().
TensorFlow中图像操作的惯例是,所有图像都应成批显示,因此它们是具有[成批、高度、宽度、通道]索引的四维数组。因为我们只有一个图像,所以我们必须在ExpandDims()开头添加一个1的批处理维度。
auto dims_expander = ExpandDims(root, float_caster, 0);
// Bilinearly resize the image to fit the required dimensions.双线性调整图像大小以适应所需尺寸。
auto resized = ResizeBilinear(
root, dims_expander,
Const(root.WithOpName("size"), {input_height, input_width}));
// Subtract the mean and divide by the scale.减去平均值,然后除以刻度。
Div(root.WithOpName(output_name), Sub(root, resized, {input_mean}),
{input_std});
// This runs the GraphDef network definition that we've just constructed, and
// returns the results in the output tensor.它运行我们刚刚构建的GraphDef网络定义,并在输出张量中返回结果。
tensorflow::GraphDef graph;
TF_RETURN_IF_ERROR(root.ToGraphDef(&graph));
std::unique_ptr<tensorflow::Session> session(
tensorflow::NewSession(tensorflow::SessionOptions()));
TF_RETURN_IF_ERROR(session->Create(graph));
TF_RETURN_IF_ERROR(session->Run({inputs}, {output_name}, {}, out_tensors));
return Status::OK();
}