What does this mean and how can I train my own images

I've inputted following with the correct map with images.

```
python main.py --dataset=test --input_fname_pattern="*.png" --train
{'batch_size': 64,
'beta1': 0.5,
'checkpoint_dir': 'checkpoint',
'crop': False,
'dataset': 'test',
'epoch': 25,
'input_fname_pattern': '*.png',
'input_height': 108,
'input_width': None,
'learning_rate': 0.0002,
'output_height': 64,
'output_width': None,
'sample_dir': 'samples',
'train': True,
'train_size': inf,
'visualize': False}
2017-05-31 22:59:00.428564: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-05-31 22:59:00.428580: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-05-31 22:59:00.428585: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-05-31 22:59:00.428588: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-05-31 22:59:00.428592: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
Traceback (most recent call last):
File "main.py", line 97, in
tf.app.run()
File "/Users/quintendewilde/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "main.py", line 75, in main
sample_dir=FLAGS.sample_dir)
File "/Users/quintendewilde/projects/DCGAN-tensorflow/model.py", line 82, in __init__
self.build_model()
File "/Users/quintendewilde/projects/DCGAN-tensorflow/model.py", line 118, in build_model
self.D_, self.D_logits_ = self.discriminator(self.G, reuse=True)
File "/Users/quintendewilde/projects/DCGAN-tensorflow/model.py", line 332, in discriminator
h4 = linear(tf.reshape(h3, [self.batch_size, -1]), 1, 'd_h3_lin')
File "/Users/quintendewilde/projects/DCGAN-tensorflow/ops.py", line 98, in linear
tf.random_normal_initializer(stddev=stddev))
File "/Users/quintendewilde/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 1049, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/Users/quintendewilde/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 948, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/Users/quintendewilde/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 356, in get_variable
validate_shape=validate_shape, use_resource=use_resource)
File "/Users/quintendewilde/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 341, in _true_getter
use_resource=use_resource)
File "/Users/quintendewilde/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 658, in _get_single_variable
found_var.get_shape()))
ValueError: Trying to share variable discriminator/d_h3_lin/Matrix, but specified shape (8192, 1) and found shape (25088, 1).

```

Start with the documented command and dataset layout, then trace the failure from main.py through model.py's discriminator and ops.py's linear function. Compare the configured image dimensions with the shapes shown in the variable-sharing error; done means the training command runs with the intended image size or the required configuration is clearly documented.

Written by the indexing model from the issue text.