python之如何将恢复图的输出张量连接到 tensorflow 中默认图的输入

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  

而且我可以在新文件 test.py 中成功地将此模型恢复为默认图形:

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“输出”传递到新网络(python 代码，而不是恢复图)，如下所示:

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，当我将张量 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) 不是该图的元素

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类似的东西(即 connect input and output tensors of two different graphs tensorflow )。但我认为还是很不一样。

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。

请您参考如下方法:

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

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。