Question: why it generates 100 times the same image (under samples/test_arange_n.png)?

Hi, I'm using my own dataset with only 9 images, with this configuration:

```python
flags.DEFINE_integer("epoch", 40, "Epoch to train [40]")
flags.DEFINE_float("learning_rate", 0.0002, "Learning rate of for adam [0.0002]")
flags.DEFINE_float("beta1", 0.5, "Momentum term of adam [0.5]")
flags.DEFINE_integer("train_size", np.inf, "The size of train images [np.inf]")
flags.DEFINE_integer("batch_size", 1, "The size of batch images [1]")
flags.DEFINE_integer("input_height", 224, "The size of image to use (will be center cropped). [108]")
flags.DEFINE_integer("input_width", 256, "The size of image to use (will be center cropped). If None, same value as input_height [None]")
flags.DEFINE_integer("output_height", 224, "The size of the output images to produce [64]")
flags.DEFINE_integer("output_width", 256, "The size of the output images to produce. If None, same value as output_height [None]")
flags.DEFINE_string("dataset", "TEST_SET", "The name of dataset [TEST_SET]")
flags.DEFINE_string("input_fname_pattern", "*.jpg", "Glob pattern of filename of input images [*]")
flags.DEFINE_string("checkpoint_dir", "checkpoint", "Directory name to save the checkpoints [checkpoint]")
flags.DEFINE_string("sample_dir", "samples", "Directory name to save the image samples [samples]")
flags.DEFINE_boolean("train", True, "True for training, False for testing [False]")
flags.DEFINE_boolean("crop", False, "True for training, False for testing [False]")
flags.DEFINE_boolean("visualize", False, "True for visualizing, False for nothing [False]")
```
But this is generating 100 times the same image: `samples/test_arange_0.png`, `samples/test_arange_1.png`, ..., `samples/test_arange_99.png`. Also, my g_loss is always zero.

Can someone explain why it happens?

Thank you for your time!

Reproduce the report with the nine-image dataset and the listed training flags, checking samples/test_arange_0.png through samples/test_arange_99.png and the g_loss value. Trace the training and sample-generation entry points associated with these flags to determine why identical outputs are produced and why g_loss remains zero. Done means the cause is identified and the behavior is explained or corrected.

Written by the indexing model from the issue text.