simoninithomas / catdcgan Goto Github PK

can you tell me how to change size to 256 x 256?

Hi I was running this code on the same Cat dataset, everything is good but I am getting an error regarding losses variable return by the train function.
Can you please fix this error.
I am attaching the error report below

NameError Traceback (most recent call last)
in ()
4 with tf.Graph().as_default():
5 losses, samples = train(epochs, batch_size, z_dim, learning_rate_D, learning_rate_G, beta1,
----> 6 dataset.get_batches, dataset.shape, dataset.image_mode, alpha)

in train(epoch_count, batch_size, z_dim, learning_rate_D, learning_rate_G, beta1, get_batches, data_shape, data_image_mode, alpha)
81
82
---> 83 return losses, samples

NameError: name 'losses' is not defined

Hi

the train function returns two variables losses and samples. These two variables are never declared before. The article and documentation also don't explain these variables enough so I could fix it. Could you tell me how they should be declared and used?

python: can't open file 'preprocess_cat_dataset.py': [Errno 2] No such file or directory
rm: cannot remove 'cat_dataset': No such file or directory

Hi Thomas,

Great work with this, was trying myself to change the Udacity DCGAN to accept new data with no luck, was happy too see someone had cracked it :-)

But have run into a few problems:

1. First time def train reaches i=1500 program crashes with the following error:

NameError Traceback (most recent call last)
in ()
4 with tf.Graph().as_default():
5 losses, samples = train(epochs, batch_size, z_dim, learning_rate_D, learning_rate_G, beta1, dataset.get_batches,
----> 6 dataset.shape, dataset.image_mode, alpha)

in train(epoch_count, batch_size, z_dim, learning_rate_D, learning_rate_G, beta1, get_batches, data_shape, data_image_mode, alpha)
80
81
---> 82 return losses, samples

NameError: name 'losses' is not defined

2. Set from_checkpoint = True and received following error when running tf.graph():
   INFO:tensorflow:Restoring parameters from ./models/model.ckpt

UnboundLocalError Traceback (most recent call last)
in ()
4 with tf.Graph().as_default():
5 losses, samples = train(epochs, batch_size, z_dim, learning_rate_D, learning_rate_G, beta1, dataset.get_batches,
----> 6 dataset.shape, dataset.image_mode, alpha)

in train(epoch_count, batch_size, z_dim, learning_rate_D, learning_rate_G, beta1, get_batches, data_shape, data_image_mode, alpha)
35
36
---> 37 show_generator_output(sess, 4, input_z, data_shape[3], data_image_mode, image_path, True, False)
38
39 else:

UnboundLocalError: local variable 'image_path' referenced before assignment

I am running on a local machine with GPU and Tensorflow version 1.8.0