Tensorflow变量 - 添加到相同名称

时间:2016-08-16 23:13:26

标签: tensorflow

在以下几行中,有人可以确认Tensorflow添加到单个loss张量,而不是创建多个张量(全部名为loss)?

loss = tf.nn.l2_loss(a)    
loss = tf.add(loss, tf.nn.l2_loss(b))
loss = tf.add(loss, tf.nn.l2_loss(c))

谢谢!

1 个答案:

答案 0 :(得分:2)

以下是您要创建的图表。每次执行tf.<something>时,它都会附加到默认图表。也就是说,从图表中可以看出它实际上具有总结三个loss个节点enter image description here

的效果

使用此代码生成

from IPython.display import clear_output, Image, display, HTML

def strip_consts(graph_def, max_const_size=32):
    """Strip large constant values from graph_def."""
    strip_def = tf.GraphDef()
    for n0 in graph_def.node:
        n = strip_def.node.add() 
        n.MergeFrom(n0)
        if n.op == 'Const':
            tensor = n.attr['value'].tensor
            size = len(tensor.tensor_content)
            if size > max_const_size:
                tensor.tensor_content = "<stripped %d bytes>"%size
    return strip_def

def show_graph(graph_def, max_const_size=32):
    """Visualize TensorFlow graph."""
    if hasattr(graph_def, 'as_graph_def'):
        graph_def = graph_def.as_graph_def()
    strip_def = strip_consts(graph_def, max_const_size=max_const_size)
    code = """
        <script>
          function load() {{
            document.getElementById("{id}").pbtxt = {data};
          }}
        </script>
        <link rel="import" href="https://tensorboard.appspot.com/tf-graph-basic.build.html" onload=load()>
        <div style="height:600px">
          <tf-graph-basic id="{id}"></tf-graph-basic>
        </div>
    """.format(data=repr(str(strip_def)), id='graph'+str(np.random.rand()))

    iframe = """
        <iframe seamless style="width:1200px;height:620px;border:0" srcdoc="{}"></iframe>
    """.format(code.replace('"', '&quot;'))
    display(HTML(iframe))

import tensorflow as tf
import numpy as np
tf.reset_default_graph()
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
c = tf.placeholder(tf.float32)

loss = tf.nn.l2_loss(a)    
loss = tf.add(loss, tf.nn.l2_loss(b))
loss = tf.add(loss, tf.nn.l2_loss(c))

show_graph(tf.get_default_graph().as_graph_def())