ValueError: Cannot feed value of shape ..

這里x_,y_是兩個數字，當我運行時

with tf.Session() as sess:  #定義session對象生成器
    for step in range(201) :
        sess.run(train,feed_dict = {x: x_data,y: y_data})

遇到了

Traceback (most recent call last):
  File "/home/wbt1995/PycharmProjects/tensorflow_demo/tensor_pingmian.py", line 20, in <module>
    sess.run(train, feed_dict={x: x_data, y: y_data})
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 905, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1113, in _run
    str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (100,) for Tensor u'add:0', which has shape '(1, 100)'

 

其實原因很簡單，我這里的feed需要(1,100)的矩陣，也就是一維的且只有一個元素的矩陣,但[x_]和[y_]在tensorflow里會被認為是一維的但元素個數不知。
因為在給函數傳參數shape時需要傳遞形狀，如shape=[2,2],表示2維矩陣，每個維度有兩個元素，只是代表形狀，不是具體的矩陣
當傳遞給feed里面的占位符時，需要實際具體的矩陣而不是形狀，如傳二維的矩陣：x_data:[[1,1],[1,1]]

總之形狀和實際具體矩陣不要弄混