在我的代码中如下:
batch_xs, batch_ys = read_and_decode(tfrecords_file, batch_size = BATCH_SIZE)
session.run(optimizer, feed_dict = {xs: batch_xs, ys: batch_ys})
read_and_decode的输出batch_xs 和 batch_ys 都是[BATCH_SIZE, 35, 35] 的Tensor,
类型是Uint8;而 xs, ys都是 tf.placeholder(tf.float32, [BATCH_SIZE, 35, 35, 1])
报错是:TypeError:'The value of a feed cannot be a tf.Tensor object. '
本人TensorFlow入门菜鸟一只,求问大神们这里该如何改?