Models: Suggestions for autoencoder

[linrio]

Please let us know which model this issue is about (specify the top-level directory) autoencoder

In _models/autoencoder/AdditiveGaussianNoiseAutoencoderRunner.py_
Changing

    # Display logs per epoch step
    if epoch % display_step == 0:
        print "Epoch:", '%04d' % (epoch + 1), \
            "cost=", "{:.9f}".format(avg_cost)

print "Total cost: " + str(autoencoder.calc_total_cost(X_test))

to

    # Display logs per epoch step
    if epoch % display_step == 0:
        print("Epoch:", '%04d' % (epoch + 1), \
            "cost=", "{:.9f}".format(avg_cost))

print("Total cost: " + str(autoencoder.calc_total_cost(X_test)))

Also for _models/autoencoder/AutoencoderRunner.py_ , _MaskingNoiseAutoencoderRunner.py_ and _VariationalAutoencoderRunner.py_

[girving]

Would you be interesting in submitting a PR?

[linrio]

1. What's the means of PR? I'd be glad to give contributions.

2. Meanwhile giving some advice :
   In _models/autoencoder/autoencoder_models/Autoencoder.py_
   Changing

     init = tf.initialize_all_variables()

to

    init = tf.global_variables_initializer()

Also for _models/autoencoder/autoencoder_models/DenoisingAutoencoder.py_ and _models/autoencoder/autoencoder_models/VariationalAutoencoder.py_ .

[soloice]

@linrio PR means Pull Request. That is, you fork the repo, make your own commit, and request tensorflow developers to merge your contribution to the tensorflow master version.

[girving]

@linrio Yep, PR means pull request, which means contribution. The fixes in (2) look good too.

[linrio]

@soloice @girving Ok. I'll try to submit a PR.

[gunan]

@linrio any updates?

[karmel]

Automatically closing due to lack of recent activity. Please update the issue when new information becomes available, and we will reopen the issue. Thanks!