Problem while testing

I wanted to test tensorflow model of DCGAN. First, I downloaded the mnist dataset and extracted all of them and I put the extracted files in the "data" folder. So the data directory is like this:
{data} ->{mnist} -> { t10k-images-idx3-ubyte(folder) , t10k-labels-idx1-ubyte(folder), train-images-idx3-ubyte(folder), train-labels-idx1-ubyte(folder)} and inside these folders, there are the related mnist binary file.

So after that, I wanted to test the model with command:
"python main.py --dataset mnist --input_height=28 --output_height=28"

However, I am receiving this error:

>

{'batch_size':

64,
'beta1': 0.5,
'checkpoint_dir': 'checkpoint',
'crop': False,
'dataset': 'mnist',
'epoch': 25,
'input_fname_pattern': '*.jpg',
'input_height': 28,
'input_width': None,
'learning_rate': 0.0002,
'output_height': 28,
'output_width': None,
'sample_dir': 'samples',
'train': False,
'train_size': inf,
'visualize': False}
2017-05-19 06:39:26.142508: W c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow li
brary wasn't compiled to use SSE instructions, but these are available on your m
achine and could speed up CPU computations.
2017-05-19 06:39:26.142773: W c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow li
brary wasn't compiled to use SSE2 instructions, but these are available on your
machine and could speed up CPU computations.
2017-05-19 06:39:26.142990: W c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow li
brary wasn't compiled to use SSE3 instructions, but these are available on your
machine and could speed up CPU computations.
2017-05-19 06:39:26.143212: W c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow li
brary wasn't compiled to use SSE4.1 instructions, but these are available on you
r machine and could speed up CPU computations.
2017-05-19 06:39:26.143558: W c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow li
brary wasn't compiled to use SSE4.2 instructions, but these are available on you
r machine and could speed up CPU computations.
2017-05-19 06:39:26.143833: W c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow li
brary wasn't compiled to use AVX instructions, but these are available on your m
achine and could speed up CPU computations.
2017-05-19 06:39:26.144102: W c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow li
brary wasn't compiled to use AVX2 instructions, but these are available on your
machine and could speed up CPU computations.
2017-05-19 06:39:26.144438: W c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow li
brary wasn't compiled to use FMA instructions, but these are available on your m
achine and could speed up CPU computations.
2017-05-19 06:39:26.219026: I c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:887] Found device
0 with properties:
name: GeForce 820M
major: 2 minor: 1 memoryClockRate (GHz) 1.25
pciBusID 0000:03:00.0
Total memory: 2.00GiB
Free memory: 1.94GiB
2017-05-19 06:39:26.219532: I c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:908] DMA: 0
2017-05-19 06:39:26.219721: I c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:918] 0: Y
2017-05-19 06:39:26.219874: I c:\tf_jenkins\home\workspace\release-win\device\gp
u\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:950] Ignoring visi
ble gpu device (device: 0, name: GeForce 820M, pci bus id: 0000:03:00.0) with Cu
da compute capability 2.1. The minimum required Cuda capability is 3.0.
Traceback (most recent call last):
File "main.py", line 97, in
tf.app.run()
File "C:\Users\vafaee\Miniconda2\envs\tensorflow35\lib\site-packages\tensorflo
w\python\platform\app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "main.py", line 61, in main
sample_dir=FLAGS.sample_dir)
File "C:\Users\vafaee\Documents\DCGAN-tensorflow-master\DCGAN-tensorflow-maste
r\model.py", line 74, in __init__
self.data_X, self.data_y = self.load_mnist()
File "C:\Users\vafaee\Documents\DCGAN-tensorflow-master\DCGAN-tensorflow-maste
r\model.py", line 467, in load_mnist
fd = open(os.path.join(data_dir,'train-images-idx3-ubyte'))
PermissionError: [Errno 13] Permission denied: './data\\mnist\\train-images-idx3
-ubyte'

I am running the command prompt as administrator but I was not able to solve it by looking for previous questions. I am using windows 8 and I am running the code via a coda environment.

I appreciate any help regarding this issue.

@carpedm20