-
Notifications
You must be signed in to change notification settings - Fork 7.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[GSoC] StackGAN Model #77
base: master
Are you sure you want to change the base?
Conversation
Vishal-V
commented
Jul 22, 2019
- StackGAN model implementation as part of GSoC 2019 proposal.
- The model has been implemented from the paper.
- The code follows the recommended python guidelines and is compatible with the TF 2.0 beta release.
- The code has been tested and all bugs have been fixed for both Stage 1 and Stage 2 of the StackGAN.
- The architecture list is present in the README file and all dependencies can be downloaded from the requirements.txt file.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Again, I'll have to review this in more detail.
Mostly it looks great.
Was this written from scratch, or adapted from elsewhere?
# See the License for the specific language governing permissions and | ||
# limitations under the License. | ||
# ============================================================================== | ||
"""Sample runner Code. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
if __name__=="__main__":
It could be even better to have a .ipynb driver for this as well.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I will create a notebook after uploading the trained weights and modify the code to draw inferences. The official implementation of StackGAN [GitHub Link] is quite outdated and wanted to create a model of that pedigree. Thus, will train the model and upload a driver notebook that shows how to train or draw inferences from this.