segmentation model from digits

I have a question.

I try to learn my data(segmentation) from digits

but, There is same error always.

Do you know about below error message??

from model import Tower
from utils import model_property
import tensorflow as tf
import tensorflow.contrib.slim as slim
import utils as digits

class UserModel(Tower):

@model_property
def inference(self):
    x = tf.reshape(self.x, shape=[-1, self.input_shape[0], self.input_shape[1], self.input_shape[2]])
   
    with slim.arg_scope([slim.conv2d, slim.conv2d_transpose],
                        weights_initializer=tf.contrib.layers.xavier_initializer(),
                        weights_regularizer=slim.l2_regularizer(0.0005)):
        model = slim.conv2d(x, 32, [3, 3], padding='same', scope='conv1')
        model = slim.conv2d(model, 1024, [16, 16], padding='VALID', scope='conv2', stride=16)
        model = slim.conv2d_transpose(model, self.input_shape[2], [16, 16],stride=16, padding='VALID', activation_fn=None, scope='deconv_1')
        return model

@model_property
def loss(self):
    
    y = tf.reshape(self.y, shape=[-1, self.input_shape[0], self.input_shape[1], self.input_shape[2]])
    
    loss = digits.mse_loss(self.inference, y)
    return loss

File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py”, line 1801, in init
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 14745600 values, but the requested shape requires a multiple of 2764800
[[node val/model/loss/Reshape (defined at :27) ]]
[[node val/model/loss/loss (defined at /opt/digits/digits/tools/tensorflow/model.py:174) ]]

However, If I change loss = digits.mse_loss(self.inference, self.y), It’s ok.
But, Training result is bad (accuracy under 1%)

please give me solution

Thank you