파이썬 에러관련

!pip install tensorflow==1.12.0
import tensorflow as tf
import numpy as np
print(tf.__version__)
print(np.__version__)
 
data=np.array([[1,2,3,4],[1,1,4,0],[-1,-2,-4,2]],dtype=np.float32) #3X4
print(data)
data_x=data[:,0:3] #3x3
data_y=data[:,3:] #3x1
sess=tf.Session()
print('\n')
 
print(data_x)
 
print('\n')
print(data_y)
 
 
data_p=tf.one_hot(tf.cast(data_y,dtype=tf.int32),depth=5) #3X5
data_p=tf.reshape(data_p,shape=[-1,5])
sess=tf.Session()
print('\n')
print(sess.run(data_p))
 
 
xp=tf.placeholder(tf.float32,shape=[None,3]) #3x3
#yp=tf.placeholder(tf.float32,shape=[None,1])
wv= tf.Variable(tf.random_normal([3,1])) #3x1
 
print('\n')
 
h1=tf.matmul(xp,wv)
print(h1)
loss1= tf.nn.softmax_cross_entropy_with_logits(labels=data_p,logits=h1)
loss1= tf.reduce_mean(loss1)
train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(loss1)
sess.run(tf.global_variables_initializer())
 
 
print(sess.run(wv))
print(sess.run(train,feed_dict={xp:data_x}))
for i in range (2):
 
  print(sess.run(h1,feed_dict={xp:data_x}))
  print(sess.run(loss1,feed_dict={xp:data_x}))
 
문제 발생은 print(sess.run(train,feed_dict={xp:data_x}))에 일어납니다.
 feed_dict에 data_x값만 필요하다고 생각해서 주었으며, 아래에 오류중에 너무 길어 일부만 올리겠습니다
InvalidArgumentError: Input to reshape is a tensor with 15 values, but the requested shape has 3
	 [[{{node gradients/softmax_cross_entropy_with_logits_sg/Reshape_grad/Reshape}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](gradients/softmax_cross_entropy_with_logits_sg_grad/mul, softmax_cross_entropy_with_logits_sg/Shape_1)]]
 
During handling of the above exception, another exception occurred:
 
InvalidArgumentError                      Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1346           pass
   1347       message = error_interpolation.interpolate(message, self._graph)
-> 1348       raise type(e)(node_def, op, message)
   1349 
   1350   def _extend_graph(self):
 
InvalidArgumentError: Input to reshape is a tensor with 15 values, but the requested shape has 3
	 [[node gradients/softmax_cross_entropy_with_logits_sg/Reshape_grad/Reshape (defined at <ipython-input-2-baa84e09ed6d>:31)  = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](gradients/softmax_cross_entropy_with_logits_sg_grad/mul, softmax_cross_entropy_with_logits_sg/Shape_1)]]
 
Caused by op 'gradients/softmax_cross_entropy_with_logits_sg/Reshape_grad/Reshape', defined at:
  File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "/usr/local/lib/python3.6/dist-packages/traitlets/config/application.py", line 664, in launch_instance
다음과 같은 오류가 발생합니다.
도움 주시면 정말 감사하겠습니다 파일첨부하려고 하였으나, 파일형식문제로 첨부 못 하였습니다.