0

最近我一直在玩用 Keras，TF 编写的 CNN。不幸的是，我在那里遇到了一个问题：

在我强烈推荐的这些精彩的教程（https://github.com/Hvass-Labs/TensorFlow-Tutorials/blob/master/vgg16.py；其余代码在这里）中，maestro 加载预训练的 vgg16.tfmodel以非常非常丑陋的方式。

def __init__(self):
    # Now load the model from file. The way TensorFlow
    # does this is confusing and requires several steps.

    # Create a new TensorFlow computational graph.
    self.graph = tf.Graph()

    # Set the new graph as the default.
    with self.graph.as_default():

        # TensorFlow graphs are saved to disk as so-called Protocol Buffers
        # aka. proto-bufs which is a file-format that works on multiple
        # platforms. In this case it is saved as a binary file.

        # Open the graph-def file for binary reading.
        path = os.path.join(data_dir, path_graph_def)
        with tf.gfile.FastGFile(path, 'rb') as file:
            # The graph-def is a saved copy of a TensorFlow graph.
            # First we need to create an empty graph-def.
            graph_def = tf.GraphDef()

            # Then we load the proto-buf file into the graph-def.
            graph_def.ParseFromString(file.read())

            # Finally we import the graph-def to the default TensorFlow graph.
            tf.import_graph_def(graph_def, name='')

            # Now self.graph holds the VGG16 model from the proto-buf file.

        # Get a reference to the tensor for inputting images to the graph.
        self.input = self.graph.get_tensor_by_name(self.tensor_name_input_image)

        # Get references to the tensors for the commonly used layers.
        self.layer_tensors = [self.graph.get_tensor_by_name(name + ":0") for name in self.layer_names]

问题是 - 我希望我自己的预训练模型以相同/相似的方式加载，所以我可以将模型放入我稍后调用的类的图中，如果可能的话，让代码的最后几行在这里工作.（意思是从图中获取想要的层的张量。）

我所有的尝试都基于从 keras 和 comp 导入的load_model 。图让我失望了。此外，我不想以完全不同的方式加载它，因为之后我将不得不更改很多代码——对于新手来说是个大问题。

好的，我希望这个问题能传达给合适的人，并且对你来说这不是太琐碎：D。

顺便说一句：我正在解决的复杂问题，为您制作图片是样式转换也在同一个 github 存储库中。（https://github.com/Hvass-Labs/TensorFlow-Tutorials/blob/master/15_Style_Transfer.ipynb）

4

1 回答 1

0

所以你想基本上将 keras 模型加载到 tensorflow 中？可以使用以下代码轻松完成：

import keras.backend as k
from keras.models import load_model
import tensorflow as tf

model = load_model("your model.h5")  # now it's in the memory of keras
with k.get_session() as sess:
    # here you have a tensorflow computational graph, view it by:
    tf.summary.FileWriter("folder name", sess.graph)

    # if you need a certain tensor do:
    sess.graph.get_tensor_by_name("tensor name")

要阅读有关 get_session 函数的信息，请单击此处

要查看图表，您需要使用tensorboard 从 FileWriter 加载文件夹，如下所示：

tensorboard --logdir path/to/folder

希望这提供了一些帮助，祝你好运！

于 2018-11-01T21:17:34.207 回答