这里x_,y_是两个数字,当我运行时python
with tf.Session() as sess: #定义session对象生成器 for step in range(201) : sess.run(train,feed_dict = {x: x_data,y: y_data})
遇到了 markdown
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)'
其实缘由很简单,我这里的feed须要(1,100)的矩阵,也就是一维的且只有一个元素的矩阵,但[x_]和[y_]在tensorflow里会被认为是一维的但元素个数不知。
由于在给函数传参数shape时须要传递形状,如shape=[2,2],表示2维矩阵,每一个维度有两个元素,只是表明形状,不是具体的矩阵
当传递给feed里面的占位符时,须要实际具体的矩阵而不是形状,如传二维的矩阵:x_data:[[1,1],[1,1]]session
总之形状和实际具体矩阵不要弄混python2.7