关于input to reshape is a tensor 的问题

for index, name in enumerate(classes):
    class_path = cwd + name +'/'
    for img_name in os.listdir(class_path):
        img_path = class_path + img_name  # 每一个图片的地址

        img = Image.open(img_path)
        img = img.resize((448, 448))
        img_raw = img.tobytes()  # 将图片转化为二进制格式
        example = tf.train.Example(features=tf.train.Features(feature={
            "label": tf.train.Feature(int64_list=tf.train.Int64List(value=[index])),
            'img_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img_raw]))
        }))  # example对象对label和image数据进行封装
        writer.write(example.SerializeToString())  # 序列化为字符串

writer.close()

img.resize((a,b))确实是与Input to reshape is a tensor with X values相关，经过多出实验的结果是：X=（a*b）*0.75，至于为什么是这样目前还不知道。

剩下的就是根据报错来改了些参数，就是tensor有些不一样。
但到了这里就不知道应该怎么改了：

Traceback (most recent call last):
  File "mobile.py", line 67, in 
    train_acc=accuracy.eval(feed_dict={x: img_xs, y_: label_xs})
  File "/home/sys-04/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 569, in eval
    return _eval_using_default_session(self, feed_dict, self.graph, session)
  File "/home/sys-04/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3741, in _eval_using_default_session
    return session.run(tensors, feed_dict)
  File "/home/sys-04/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 778, in run
    run_metadata_ptr)
  File "/home/sys-04/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 961, in _run
    % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (20,) for Tensor 'one_hot:0', which has shape '(?, 2)'

尝试了以下：

#y_ = tf.placeholder(tf.float32, shape=[None, 2])
y = tf.placeholder(tf.int32, [None])
y_ = tf.one_hot(y,2)

但是依然如此。
明天继续囖！！！