Error for running with TensorFlow: ValueError: Variable d_w1/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

[heathervica]

Hello, please maybe could you help me? I had a running for running, I tried to figurate how to solve but I could not, I tried also with Python 2, 3.5, 3.6, And Tensorflow 1 and 1.1

The complete Error was:
heather@heather-ThinkPad-P50:~/Downloads/generative-adversarial-networks-master (2)$ python3 gan-script.py
Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
Traceback (most recent call last):
File "gan-script.py", line 131, in
d_trainer_fake = tf.train.AdamOptimizer(0.0003).minimize(d_loss_fake, var_list=d_vars)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 325, in minimize
name=name)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 446, in apply_gradients
self._create_slots([_get_variable_for(v) for v in var_list])
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/adam.py", line 122, in _create_slots
self._zeros_slot(v, "m", self._name)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 766, in _zeros_slot
named_slots[_var_key(var)] = slot_creator.create_zeros_slot(var, op_name)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 174, in create_zeros_slot
colocate_with_primary=colocate_with_primary)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 146, in create_slot_with_initializer
dtype)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 66, in _create_slot_var
validate_shape=validate_shape)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 1049, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 948, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 356, in get_variable
validate_shape=validate_shape, use_resource=use_resource)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 341, in _true_getter
use_resource=use_resource)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 671, in _get_single_variable
"VarScope?" % name)
ValueError:
Variable d_w1/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

[fulkast]

I made some necessary namescope fixes to run the code on my machine where I use Tensorflow 1.2.
I've submitted a PR which is here: #3

[ghost]

does anybody know how to solve this problem? unless this piece of code is useless

[RanaivosonHerimanitra]

Restart and run kernel using the following inplace of cell number 4 of the original notebook:

sess = tf.Session() 
batch_size = 50 
z_dimensions = 100 
x_placeholder = tf.placeholder("float", shape = [None,28,28,1], name='x_placeholder') 
Gz = generator(batch_size, z_dimensions) 
Dx = discriminator(x_placeholder) 
with tf.variable_scope(tf.get_variable_scope()) as scope:
    pass 
Dg = discriminator(Gz, reuse=True)
g_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=Dg, labels=tf.ones_like(Dg))) 
d_loss_real = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=Dx, labels=tf.fill([batch_size, 1], 0.9))) 
d_loss_fake = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=Dg, labels=tf.zeros_like(Dg))) 
d_loss = d_loss_real + d_loss_fake 
tvars = tf.trainable_variables() 
d_vars = [var for var in tvars if  'd_' in var.name] 
g_vars = [var for var in tvars if not 'g_' in var.name] 

with tf.variable_scope(scope):    
    d_trainer_fake = tf.train.AdamOptimizer(0.0001).minimize(d_loss_fake, var_list=d_vars) 
    d_trainer_real = tf.train.AdamOptimizer(0.0001).minimize(d_loss_real, var_list=d_vars) 
    g_trainer = tf.train.AdamOptimizer(0.0001).minimize(g_loss, var_list=g_vars)
    

[pudepiedj]

The fix from RanaivosonHerimanitra solves the problem. Thank you.

[chuong98]

The fix from RanaivosonHerimanitra lets the code run, but does not yield correct result.
Change this line from his code should correct it (remove not ):

g_vars = [var for var in tvars if 'g_' in var.name]

If you also want the code run continuously, change the plt.plot part to:

            plt.imshow(im.reshape([28, 28]), cmap='Greys')
            plt.show(block=False)
            plt.pause(2)
            plt.close()

[7LFB]

with tf.variable_scope(scope,reuse=tf.AUTO_REUSE):
optimizer_step=tf.train.AdamOptimizer(0.0001).minimized(loss, var)