InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor

以下两种方式都不好使用：目前只是找到原因，等我找到方案再来完善。

From your error message, it looks like you are using IPython. One pitfall when using IPython to build a TensorFlow model is that functions like tf.merge_all_summaries() will remember every summary created in the current session, including cells that failed with an error. This is a result of TensorFlow using a default graph to collect all of the operations, summaries, etc. that are created in a process, unless you specify the graph explicitly. I suspect that your call to tf.merge_all_summaries() is returning more than the three histogram summaries that you created in your code, and the older ones will have a dependency on a previously created placeholder.

There are two main ways that you could fix that. The simplest is to explicitly merge the summaries, rather than using tf.merge_all_summaries():

weights_summary = tf.histogram_summary("weights", W)
biases_summary = tf.histogram_summary("biases", b)
y_summary = tf.histogram_summary("y", y)
merged = tf.merge_summary([weights_summary, biases_summary, y_summary])

An alternative would be to set an explicit default graph before constructing your model. This is awkward if you want to split your model across multiple IPython cells, but should also work:

# Sets a new default graph, and stores it in `g`.
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [None, 784])
# ...
# Summaries are added to `g`.
_ = tf.histogram_summary("weights", W)
_ = tf.histogram_summary("biases", b)
_ = tf.histogram_summary("y", y)
# ...
# `merged` contains only summaries from `g`.
merged = tf.merge_all_summaries()

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor相关推荐

BUG InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Pl
为了想看一段代买的Tensor,加入了 sess = tf.Session()print(sess.run(self.embedded_chars)) 然后就报错: InvalidArgumentEr ...
InvalidArgumentError: You must feed a value for placeholder tensor ‘conv2d_12_input‘ with dtype floa
InvalidArgumentError: You must feed a value for placeholder tensor 'conv2d_12_input' with dtype 在jup ...
坑之 You must feed a value for placeholder tensor ‘label_input‘ with dtype float and shape
首先检查图中的tf.placeholder(),你在sess.run的时候是否feed满足dtype和shape的数据.如果你这两项都没错的话,那么你极有可能犯了重命名的错误,这里指的是使用占位符生成 ...
tensorflow错误：InvalidArgumentError (see above for traceback): Cannot assign a device for operation
一.错误 InvalidArgumentError (see above for traceback): Cannot assign a device for operation 'shuffle_b ...
tensorflow报InvalidArgumentError (see above for traceback): Conv2DSlowBackpropInput
在使用TensorFlow求解转置卷积(反卷积)的时候,我们需要调用tf.nn.conv2d_transpose方法,在计算反卷积的时候,报了如下错误 InvalidArgumentError (se ...
报错InvalidArgumentError (see above for traceback): Restoring from checkpoint failed
报错详情: 使用faster-rcnn训练自己的模型,下载使用别人的代码这份代码运行python tools/demo.py报错如下: Traceback (most recent call l ...
The value of a feed cannot be a tf.Tensor object.
使用tf.data.Dataset时出现报错"The value of a feed cannot be a tf.Tensor object." session.run(trai ...
InvalidArgumentError (see above for traceback): Invalid JPEG data, size 75244
除了这一句之外上面应该还有一句:Not a JPEG file: starts with 0x47 0x49 starts with 0x47 0x49说明这是一张gif图像,starts with ...
简单完整地讲解tensorflow模型的保存和恢复
http://blog.csdn.net/liangyihuai/article/details/78515913 在本教程主要讲到: 1. 什么是Tensorflow模型? 2. 如何保存Tenso ...

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor相关推荐

最新文章

热门文章