i solved this problem

firstly, upgrade tensorflow to R1.0.1
and move run_exp.py file /home/username/StackGAN/stageI to /home/username/StackGAN

second, install dependencies
$ pip install prettytensor
$ pip install easydict
$ pip install progressbar

third, upgrade code(misc, stageI, and stageII folder python codes) using tf_upgrade
(see : https://www.tensorflow.org/install/migration)

fourth, change misc/datasets.py
line 75, 76

h1 = np.floor((ori_size - self._imsize) * np.random.random())
w1 = np.floor((ori_size - self._imsize) * np.random.random())

to

h1 = int(np.floor((ori_size - self._imsize) * np.random.random()))
w1 = int(np.floor((ori_size - self._imsize) * np.random.random()))

now, i'm training dataset with

CPU : intel core i5-7600
GPU : Geforce GTX1060 (6GB ram)
with CUDA 8.0m cuDNN 5.1, Tensorflow-gpu 1.0.1

I also found it was tf version issue.
Upgrading tf to higher version would solve the issue.

HOWEVER, if you upgrad the tf version into 1.0.1, you will get type error since tf 1.0.1 version have changed the argument order of tf.concat function. (google/prettytensor#48)

To avoid this error, you have to change the argument order of tf.concat (i.e. tf.concat(1, [c,z]) --> tf.concat[c,z], 1)

If you want modified stable version of this code, refer to my repo
(Same code with the author, but fixed bugs.)

@seongkyun thank you nery much ! it really works !

@leeeeeeo can you give me details of solution?Thanks a lot.

@seongkyun @nashory can you tell me your tensorflow version?I want to run the stackGAN,but i am confused about how to configure the environment.Thanks a lot.

@chaowentao version has already shown at the last of @seongkyun 's comment. and it really works. just follow his solution.

@leeeeeeo thank you.I'll try it.

@leeeeeeo Do i still need to redo the images processing?

@chaowentao maybe. i did.

@leeeeeeo my result is
W tensorflow/core/framework/op_kernel.cc:993] Internal: Failed launching ResizeNearestNeighbor
[[Node: g_net/apply_5/ResizeNearestNeighbor = ResizeNearestNeighbor[T=DT_FLOAT, align_corners=false, _device="/job:localhost/replica:0/task:0/gpu:0"](g_net/apply_4/Relu, g_net/apply_5/ResizeNearestNeighbor/size)]]
W tensorflow/core/framework/op_kernel.cc:993] Internal: Failed launching ResizeNearestNeighbor
[[Node: g_net/apply_5/ResizeNearestNeighbor = ResizeNearestNeighbor[T=DT_FLOAT, align_corners=false, _device="/job:localhost/replica:0/task:0/gpu:0"](g_net/apply_4/Relu, g_net/apply_5/ResizeNearestNeighbor/size)]]
Can you give me some advice?
ubuntu14.04LTS CUDA 8.0m cuDNN 5.1, Tensorflow-gpu 1.0.1

@chaowentao somewhere went wrong. i didnt meet this. try again.

its a version problem：
just change the version of tensorflow and prettytensor
pip install tensorflow-gpu==0.12.0rc0
pip install prettytensor==0.7.1