streamlit / demo-face-gan

A demonstration of using a live Tensorflow session to create an interactive face-GAN explorer.

Streamlit Demo: The Controllable GAN Face Generator

This project highlights Streamlit's new st.experimental_memo() and st.experimental_singleton() features with an app that calls on TensorFlow to generate photorealistic faces, using Nvidia's Progressive Growing of GANs and Shaobo Guan's Transparent Latent-space GAN method for tuning the output face's characteristics. For more information, check out the tutorial on Towards Data Science.

The Streamlit app is implemented in only 150 lines of Python and demonstrates the wide new range of objects that can be used safely and efficiently in Streamlit apps.

How to run this demo

The demo requires Python 3.6 or 3.7 (The version of TensorFlow we use is not supported in Python 3.8+). We suggest creating a new virtual environment, then running:

git clone https://github.com/streamlit/demo-face-gan.git
cd demo-face-gan
poetry install
poetry run streamlit run streamlit_app.py

Model Bias

Playing with the sliders, you will find biases that exist in this model. For example, moving the Smiling slider can turn a face from masculine to feminine or from lighter skin to darker. Apps like these that allow you to visually inspect model inputs help you find these biases so you can address them in your model before it's put into production.

Questions? Comments?

Please ask in the Streamlit community or check out our article.

demo-face-gan's Issues

Issue: The app transforms white man into black when smiling parameter is reduced

The webapp is transforming the face of a white man to a black man when the 'Smiling' is reduced to 0 .

This can be considered Racist (where no smiling is being indicated a trait of a Black man) and should be fixed to avoid backlash in future.

To reproduce:

• Select Young as 60
• Select Smiling as 90
• Select Male as 100
• Now drop Smiling to 0 .

TF already compatible with Python 3.7

Hi, just tried it and works with Python 3.7, so that should not be an issue anymore, that way you can reduce friction to try the demo.

Btw, great work and awesome Streamlit If you can deploy it even better to evangelize.

Update to Python 3.8?

What would we need to change in order to make the demo work with Python 3.8?

missing requirements.txt

Can't find requirements.txt.

thanks,

Robin

Could not find a version that satisfies the requirement tensorflow==1.15.2

After running requirements.txt I was not able to run streamlit. Is there another Tensorflow version compatible?

Not working with CPU (UnimplementedError: The Conv2D op currently only supports the NHWC tensor format on the CPU. The op was given the format: NCHW)

Missing requirements.txt

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

AttributeError: module 'google.protobuf.descriptor' has no attribute '_internal_create_key'

On cloning and running on my local machine, after following each step clearly, I get the following message:

Traceback (most recent call last):
  File "c:\users\raghav khullar\appdata\local\programs\python\python37\lib\runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "c:\users\raghav khullar\appdata\local\programs\python\python37\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "C:\Users\Raghav Khullar\AppData\Local\Programs\Python\Python37\Scripts\streamlit.exe\__main__.py", line 4, in <module>
  File "c:\users\raghav khullar\appdata\local\programs\python\python37\lib\site-packages\streamlit\__init__.py", line 75, in <module>
    from streamlit.delta_generator import DeltaGenerator as _DeltaGenerator
  File "c:\users\raghav khullar\appdata\local\programs\python\python37\lib\site-packages\streamlit\delta_generator.py", line 25, in <module>
    from streamlit.proto import Block_pb2
  File "c:\users\raghav khullar\appdata\local\programs\python\python37\lib\site-packages\streamlit\proto\Block_pb2.py", line 21, in <module>
    create_key=_descriptor._internal_create_key,
AttributeError: module 'google.protobuf.descriptor' has no attribute '_internal_create_key'

How can I resolve this?

How to resolve tensorflow version mismatch with Python 3.8

How do I resolve this error?

ERROR: Could not find a version that satisfies the requirement tensorflow==1.15.2 (from -r requirements.txt (line 14)) (from versions: 2.2.0rc3, 2.2.0rc4, 2.2.0, 2.3.0rc0, 2.3.0rc1, 2.3.0rc2, 2.3.0)
ERROR: No matching distribution found for tensorflow==1.15.2 (from -r requirements.txt (line 14))

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

"open in streamlit" app is broken?

Thanks for providing this cool open-source tool to the community! 👏

I wanted to try out streamlit without installing it locally so I clicked this badge:

The app started up fine, but if I changed any of the sliders, I just got a missing image icon.

Not sure if I have done something wrong or if this is a bug...

ModuleNotFoundError: No module named 'feature_axis'

File "c:\users\asus\appdata\local\programs\python\python37\lib\site-packages\streamlit\ScriptRunner.py", line 319, in _run_script
exec(code, module.dict)
File "C:\Users\asus\PycharmProjects\streamlit_project\demo_face_gan_project.py", line 9, in
import feature_axis

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

After installing packages manually, it still does not run.

Maybe more packages missing or 3.10 not supported.

Python version

(venv) 08:54:38|C|demo-face-gan> python --version
Python 3.10.0

My requirements.txt
requirements.txt

Error

2022-08-11 08:43:47.223040: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-08-11 08:43:47.223212: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
C:\Users\HaraldEllingsen\demo-face-gan\pg_gan\tfutil.py:179: SyntaxWarning: "is" with a literal. Did you mean "=="?
  if v.shape.ndims is 0:
C:\Users\HaraldEllingsen\demo-face-gan\pg_gan\tfutil.py:181: SyntaxWarning: "is" with a literal. Did you mean "=="?
  elif v.shape.ndims is 1:
C:\Users\HaraldEllingsen\demo-face-gan\pg_gan\tfutil_cpu.py:179: SyntaxWarning: "is" with a literal. Did you mean "=="?
  if v.shape.ndims is 0:
C:\Users\HaraldEllingsen\demo-face-gan\pg_gan\tfutil_cpu.py:181: SyntaxWarning: "is" with a literal. Did you mean "=="?
  elif v.shape.ndims is 1:
2022-08-11 08:44:55.899 Uncaught app exception
Traceback (most recent call last):
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\caching\cache_utils.py", line 126, in get_or_create_cached_value
    return_value = cache.read_value(value_key)
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\caching\singleton_decorator.py", line 262, in read_value
    raise CacheKeyNotFoundError()
streamlit.caching.cache_errors.CacheKeyNotFoundError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\scriptrunner\script_runner.py", line 557, in _run_script
    exec(code, module.__dict__)
  File "C:\Users\HaraldEllingsen\demo-face-gan\streamlit_app.py", line 227, in <module>
    main()
[requirements.txt](https://github.com/streamlit/demo-face-gan/files/9306758/requirements.txt)

  File "C:\Users\HaraldEllingsen\demo-face-gan\streamlit_app.py", line 28, in main
    session, pg_gan_model = load_pg_gan_model()
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\caching\cache_utils.py", line 145, in wrapper
    return get_or_create_cached_value()
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\caching\cache_utils.py", line 137, in get_or_create_cached_value
    return_value = func(*args, **kwargs)
  File "C:\Users\HaraldEllingsen\demo-face-gan\streamlit_app.py", line 137, in load_pg_gan_model
    config = tf.ConfigProto(allow_soft_placement=True)
AttributeError: module 'tensorflow' has no attribute 'ConfigProto'
2022-08-11 08:45:05.428 Uncaught app exception
Traceback (most recent call last):
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\caching\cache_utils.py", line 126, in get_or_create_cached_value
    return_value = cache.read_value(value_key)
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\caching\singleton_decorator.py", line 262, in read_value
    raise CacheKeyNotFoundError()
streamlit.caching.cache_errors.CacheKeyNotFoundError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\scriptrunner\script_runner.py", line 557, in _run_script
    exec(code, module.__dict__)
  File "C:\Users\HaraldEllingsen\demo-face-gan\streamlit_app.py", line 227, in <module>
    main()
  File "C:\Users\HaraldEllingsen\demo-face-gan\streamlit_app.py", line 28, in main
    session, pg_gan_model = load_pg_gan_model()
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\caching\cache_utils.py", line 145, in wrapper
    return get_or_create_cached_value()
  File "C:\Users\HaraldEllingsen\demo-face-gan\venv\lib\site-packages\streamlit\caching\cache_utils.py", line 137, in get_or_create_cached_value
    return_value = func(*args, **kwargs)
  File "C:\Users\HaraldEllingsen\demo-face-gan\streamlit_app.py", line 137, in load_pg_gan_model
    config = tf.ConfigProto(allow_soft_placement=True)
AttributeError: module 'tensorflow' has no attribute 'ConfigProto'

What is the difference between stylegan2 and pggan?

If stylegan is newer better can we upgrade to that?

Clicking on this demo's link in the gallery gives an error

In the Gallery page, clicking on this demo gives the error "Oh no.
Error running app. If this keeps happening, please contact support."

lmdb should be installed using conda instead of pip

In the pip version , C++ compilation could lead/is leading to wheel build errors.
The conda precompiled package solved this hassle for lmdb.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

i want to provide a local image

how can i provide local image

No requirements.txt

How do I install the right dependencies without the requirements.txt ?

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

App not working

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.

Over resource limits on Streamlit Cloud

Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.