zurutech / gans-from-theory-to-production Goto Github PK

Create separate branches for each Tensorflow version used and for each event.

Should we try and keep Projects organized or should we delete it?

If we decide to keep, we could use it to either track development or showcase a roadmap.

Add the notebook containing information on TFGAN and all the relevant code.

Add the code for the Generator and Discriminator written using the TFGAN module.

The link in the final line of 2.1. Writing a GAN from scratch.ipynb (A solution to this exercise can be found in the notebook: BONUS - Conditional GAN from scratch.) is broken.

• Load Trained Model to CloudML Engine
• Online Predictions
• Batch Predictions
• Colab Link
• Google Cloud & Cloud ML Engine logos
• Pull Request

AttributeError Traceback (most recent call last)
in
5
6 # Import tfgan from contrib
----> 7 tfgan = tf.contrib.gan

AttributeError: module 'tensorflow' has no attribute 'contrib'

! pip install tensorflow==1.13.1
Requirement already satisfied: tensorflow==1.13.1 in /usr/local/lib/python3.7/dist-packages (1.13.1)

Update the README.md

• Bump TF Version to 2.0
• Bump Python Version to 3.7
• Add @iLeW and @EmanueleGhelfi to the Authors

remote: Total 36 (delta 1), reused 24 (delta 0), pack-reused 0
fatal: cannot create directory at '1. GAN: theory and applications': Invalid argument
warning: Clone succeeded, but checkout failed.
You can inspect what was checked out with 'git status'
and retry the checkout with 'git checkout -f HEAD'