A problem about fcn8_vgg.py

[liuzhisheng1226]

When I ran fcn8_vgg.py,it throw an exception：
2017-09-06 19:42:22.785673: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Conv2DSlowBackpropInput: Size of out_backprop doesn't match computed: actual = 23, computed = 12
2017-09-06 19:42:22.785941: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Conv2DSlowBackpropInput: Size of out_backprop doesn't match computed: actual = 23, computed = 12
[[Node: content_vgg/upscore2/conv2d_transpose = Conv2DBackpropInput[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/gpu:0"](content_vgg/upscore2/stack, upscore2/up_filter/read, content_vgg/score_fr/BiasAdd)]]
......
InvalidArgumentError (see above for traceback): Conv2DSlowBackpropInput: Size of out_backprop doesn't match computed: actual = 23, computed = 12
[[Node: content_vgg/upscore2/conv2d_transpose = Conv2DBackpropInput[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/gpu:0"](content_vgg/upscore2/stack, upscore2/up_filter/read, content_vgg/score_fr/BiasAdd)]]

[jharaldson]

Line 112 in fcn8_vgg.py needs to be changed:
From:
self.pool5 = self._max_pool(self.conv4_3, 'pool4', debug)
To:
self.pool5 = self._max_pool(self.conv5_3, 'pool5', debug)

[953693623]

dear friend:
Can you tell me how to train this network? I'm new on the job and I have no idea about it.