如何将恢复图的输出张量连接到张量流中默认图的输入？

Question

刚接触tensorflow，卡在这好几天了。现在我有以下预训练模型（4 个文件）：

Classification.inception.model-27.data-0000-pf=00001
Classification.inception.model-27.index
Classification.inception.model-27.meta
checkpoint

而且我可以成功地将此模型恢复为新文件中的默认图表 test.py:

with tf.Session() as sess:
    new_restore = tf.train.import_meta_graph('Classification.inception.model-27.meta')
    new_restore.restore(sess, tf.train.latest_checkpoint('/'))
    graph = tf.get_default_graph()
    input_data = graph.get_tensor_by_name('input_data')
    output = graph.get_tensor_by_name('logits/BiasAdd:0')
    ......
    logits = sess.run(output, feed_dict = {input_data: mybatch})
    ......

上面的脚本运行良好，因为 test.py 独立于 train.py。所以我这样得到的图就是默认的图

但是，我不知道如何将这个预训练模型集成到现有图中，即将张量 "output" 传递到新网络（python 代码，而不是恢复图），例如这个：

def main():
    ### load the meta file and restore the pretrained graph here #####
    new_restore = tf.train.import_meta_graph('Classification.inception.model-27.meta')
    new_restore.restore(sess, tf.train.latest_checkpoint('/'))
    graph = tf.get_default_graph()
    input_data = graph.get_tensor_by_name('input_data')
    output1 = graph.get_tensor_by_name('logits/BiasAdd:0')
    ......
    with tf.Graph().as_default():
        with tf.variable_scope(scope, 'InceptionResnetV1', [inputs], reuse=reuse):
            with slim.arg_scope([slim.batch_norm, slim.dropout], is_training = is_training):
                with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d]):
                    net = slim.conv2d(output1, 32, 3, stride = 2, scope= 'Conv2d_1a_3x3')

但是，当我将tensor output1 传递给slim.conv2d() 时出现错误。消息是：

ValueError：Tensor("InceptionResnetV1/Conv2d_1a_3x3/BatchNorm/AssignMovingAvg:0".shape=(32,).dtype=float32_ref) 不是这个图的元素

人们通常如何处理这个问题（从 .meta 恢复一个图并将其输出张量连接到当前默认图的输入）？

我在网上搜索并发现了与我的问题相似的东西（即）。但是我觉得还是很不一样的。

此外，还有一些类似的方法可以恢复“.ckpt”文件，但我认为它们仍然不是我要找的。

如有任何意见和指导，我们将不胜感激。谢谢

Answer 1

您的问题是 with tf.Graph().as_default(): 覆盖了您的旧图表：

Another typical usage involves the tf.Graph.as_default context manager, which overrides the current default graph for the lifetime of the context.

只需删除此行即可保留旧图表：

import tensorflow as tf
import numpy as np

const_input_dummy = np.random.randn(1, 28)

# create graph and save everything
x = tf.placeholder(dtype=tf.float32, shape=[1, 28], name='plhdr')
y = tf.layers.dense(x, 2, name='logits')

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print(sess.run(y, {x: const_input_dummy}))

    saver = tf.train.Saver()
    saver.save(sess, './export/inception')

# reset everything so far (like creating another script)
tf.reset_default_graph()

# answer to question
with tf.Session() as sess:
    # import old graph structure
    restorer = tf.train.import_meta_graph('./export/inception.meta')
    # get reference to tensors from imported graph
    graph = tf.get_default_graph()
    x = graph.get_tensor_by_name("plhdr:0")
    y = graph.get_tensor_by_name('logits/BiasAdd:0')

    # add some new operations (and variables)
    with tf.variable_scope('new_scope'):
        y = tf.layers.dense(y, 1, name='other_layer')

    # init all variables ...
    sess.run(tf.global_variables_initializer())
    # ... then restore variables from file
    restorer.restore(sess, tf.train.latest_checkpoint('./export'))

    # this will execute without errors
    print(sess.run(y, {x: const_input_dummy}))

通常不需要维护多个图。所以我建议只使用一个图。

如何将恢复图的输出张量连接到张量流中默认图的输入？

How to connect the output tensor of a restored graph to the input of the default graph in tensorflow?

python

machine-learning

training-data

tensorflow

pre-trained-model