feed array
1:預設placeholder:
self.xxx = tf.placeholder(dtype=tf.float32, shape=[xxx, xxx], name='xxx')
2:喂numpy.ndarray
格式的矩陣進去:
xxx = sess.run(self.xxx, feed_dict={self.xxx: xx_array})
feed variable
1:預設placeholder:
self.xxx = tf.placeholder(dtype=tf.float32, name='xxx')
2:喂任意變量進去:
xxx = sess.run(self.xxx, feed_dict={self.xxx: xx_variable})