Also one question about how to use write_graph(): In documentations the graph_def is given by sess.graph_def but in examples in freeze_graph() it is sess.graph.as_graph_def(). What is the difference between these two?

這個(gè)問(wèn)題與這個(gè)問(wèn)題有關(guān).

謝謝！

推薦答案

這是我利用 TF 0.12 中引入的 V2 檢查點(diǎn)的解決方案.

Here's my solution utilizing the V2 checkpoints introduced in TF 0.12.

無(wú)需將所有變量轉(zhuǎn)換為常量或凍結(jié)圖表.

There's no need to convert all variables to constants or freeze the graph.

為了清楚起見(jiàn)，我的目錄 models 中的 V2 檢查點(diǎn)如下所示:

Just for clarity, a V2 checkpoint looks like this in my directory models:

checkpoint  # some information on the name of the files in the checkpoint
my-model.data-00000-of-00001  # the saved weights
my-model.index  # probably definition of data layout in the previous file
my-model.meta  # protobuf of the graph (nodes and topology info)

Python 部分(保存)

with tf.Session() as sess:
    tf.train.Saver(tf.trainable_variables()).save(sess, 'models/my-model')

如果您使用 tf.trainable_variables() 創(chuàng)建 Saver，您可以節(jié)省一些頭痛和存儲(chǔ)空間.但也許一些更復(fù)雜的模型需要保存所有數(shù)據(jù)，然后將此參數(shù)刪除到 Saver，只需確保您正在創(chuàng)建 Saver after> 您的圖表已創(chuàng)建.給所有變量/層賦予唯一的名稱也是非常明智的，否則你可能會(huì)遇到不同的問(wèn)題.

If you create the Saver with tf.trainable_variables(), you can save yourself some headache and storage space. But maybe some more complicated models need all data to be saved, then remove this argument to Saver, just make sure you're creating the Saver after your graph is created. It is also very wise to give all variables/layers unique names, otherwise you can run in different problems.

Python 部分(推理)

with tf.Session() as sess:
    saver = tf.train.import_meta_graph('models/my-model.meta')
    saver.restore(sess, tf.train.latest_checkpoint('models/'))
    outputTensors = sess.run(outputOps, feed_dict=feedDict)

C++ 部分(推理)

請(qǐng)注意，checkpointPath 不是任何現(xiàn)有文件的路徑，只是它們的公共前綴.如果您錯(cuò)誤地放置了 .index 文件的路徑，TF 不會(huì)告訴您這是錯(cuò)誤的，但是由于未初始化的變量，它會(huì)在推理過(guò)程中死亡.

Note that checkpointPath isn't a path to any of the existing files, just their common prefix. If you mistakenly put there path to the .index file, TF won't tell you that was wrong, but it will die during inference due to uninitialized variables.

#include <tensorflow/core/public/session.h>
#include <tensorflow/core/protobuf/meta_graph.pb.h>

using namespace std;
using namespace tensorflow;

...
// set up your input paths
const string pathToGraph = "models/my-model.meta"
const string checkpointPath = "models/my-model";
...

auto session = NewSession(SessionOptions());
if (session == nullptr) {
    throw runtime_error("Could not create Tensorflow session.");
}

Status status;

// Read in the protobuf graph we exported
MetaGraphDef graph_def;
status = ReadBinaryProto(Env::Default(), pathToGraph, &graph_def);
if (!status.ok()) {
    throw runtime_error("Error reading graph definition from " + pathToGraph + ": " + status.ToString());
}

// Add the graph to the session
status = session->Create(graph_def.graph_def());
if (!status.ok()) {
    throw runtime_error("Error creating graph: " + status.ToString());
}

// Read weights from the saved checkpoint
Tensor checkpointPathTensor(DT_STRING, TensorShape());
checkpointPathTensor.scalar<std::string>()() = checkpointPath;
status = session->Run(
        {{ graph_def.saver_def().filename_tensor_name(), checkpointPathTensor },},
        {},
        {graph_def.saver_def().restore_op_name()},
        nullptr);
if (!status.ok()) {
    throw runtime_error("Error loading checkpoint from " + checkpointPath + ": " + status.ToString());
}

// and run the inference to your liking
auto feedDict = ...
auto outputOps = ...
std::vector<tensorflow::Tensor> outputTensors;
status = session->Run(feedDict, outputOps, {}, &outputTensors);

這篇關(guān)于Tensorflow 在 C++ 中導(dǎo)出和運(yùn)行圖的不同方式的文章就介紹到這了，希望我們推薦的答案對(duì)大家有所幫助，也希望大家多多支持html5模板網(wǎng)！