All Projects → jonasz → Progressive_infogan

jonasz / Progressive_infogan

Progressive training of GANs with Mutual Information Penalty

Projects that are alternatives of or similar to Progressive infogan

Deeptoxic
top 1% solution to toxic comment classification challenge on Kaggle.
Stars: ✭ 180 (-1.1%)
Mutual labels:  jupyter-notebook
Berkeley Stat 157
Homepage for STAT 157 at UC Berkeley
Stars: ✭ 2,523 (+1286.26%)
Mutual labels:  jupyter-notebook
Mslearn Aml Labs
Azure Machine Learning Lab Notebooks
Stars: ✭ 182 (+0%)
Mutual labels:  jupyter-notebook
Deeplearning.ai Note
网易云课堂终于官方发布了吴恩达经过授权的汉化课程-“”深度学习专项课程“”,这是自己做的一些笔记以及代码。下为网易云学习链接
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Academiccontent
Free tech resources for faculty, students, researchers, life-long learners, and academic community builders for use in tech based courses, workshops, and hackathons.
Stars: ✭ 2,196 (+1106.59%)
Mutual labels:  jupyter-notebook
Pyro2
A framework for hydrodynamics explorations and prototyping
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Pytorch Vae
A CNN Variational Autoencoder (CNN-VAE) implemented in PyTorch
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Bert Sklearn
a sklearn wrapper for Google's BERT model
Stars: ✭ 182 (+0%)
Mutual labels:  jupyter-notebook
Infersent
InferSent sentence embeddings
Stars: ✭ 2,179 (+1097.25%)
Mutual labels:  jupyter-notebook
Feature Engineering Handbook
A practical feature engineering handbook
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Scatteract
Project which implements extraction of data from scatter plots
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Subpixel
subpixel: A subpixel convnet for super resolution with Tensorflow
Stars: ✭ 2,114 (+1061.54%)
Mutual labels:  jupyter-notebook
Hands On Data Analysis
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Machinelearning ng
吴恩达机器学习coursera课程,学习代码(2017年秋) The Stanford Coursera course on MachineLearning with Andrew Ng
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Awesome Machine Learning Jupyter Notebooks For Colab
A curated list of Machine Learning and Deep Learning tutorials in Jupyter Notebook format ready to run in Google Colaboratory
Stars: ✭ 182 (+0%)
Mutual labels:  jupyter-notebook
Eeg Notebooks v0.1
Previous version of eeg-notebooks
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Deeprl Agents
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
Stars: ✭ 2,149 (+1080.77%)
Mutual labels:  jupyter-notebook
Mathematics For Machine Learning Cousera
quizzes/assignments for mathematics for machine learning specialization on coursera
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook
Ce7454 2019
Deep learning course CE7454, 2019
Stars: ✭ 182 (+0%)
Mutual labels:  jupyter-notebook
Smoke Detect By Yolov5
Yolov5 real time smoke detection system
Stars: ✭ 181 (-0.55%)
Mutual labels:  jupyter-notebook

Progressive InfoGAN

Progressive InfoGAN combines two techniques:

What it does

  • A Generator is trained on any unlabeled high-res dataset of images. For our experiments we use CelebA-HQ.
  • After training, the Generator produces novel images, similar to those in the dataset.
  • When producing an image, we can independently control its semantic feautres. In case of CelebA-HQ, semantic features include: the direction of the look, hair color, nose shape, and much more. See Summary of selected isolated features.
  • Most importantly, these semantic features are discovered during training in a completely unsupervised fashion - no human input is required.

Under the hood

The InfoGAN technique was adapted to the progressive architecture of the model by splitting the structured code to parts, and feeding each part to the network by conditioning activations in the corresponding block of the Generator. You can find a detailed description of the architecture, along with quality assessment, in my Master's Thesis text (expected defense: Q4 2018).

Running

# Training:
# Fill in src/constants.py, and run
$ cd src
$ python jonasz/experiments/2018_08_28/exp_consistency_300.py

# Working with the trained Generator:
$ cd src
$ python -m jupyter notebook --port 5088

Now you can experiment with the generator in a notebook: src/jonasz/notebooks/generator.ipynb

Summary of selected isolated features

See also the animated, extended version of the summary at: https://youtu.be/U2okTa0JGZg. Some of the subtler changes are better visible when animated. For each of the features listed below, there is a link to the exact corresponding timestamp in the animation.

Smile: upper lip
Age
Look direction
Hair color
Left / right rotation
Face oval: size
Hairstyle: background size
Lower jaw size
Forward backward inclination
Mouth: open / closed
Hair: wavy / straight
Eyebrows: up / down
Nose length
Nose: upturned tip
Eyebrows shape
Vertical face stretch
Color of the irises
Shape of the nostrils
Hair texture
Lower eyelid
Wrinkles

A comprehensive list of all isolated features is at: https://youtu.be/mOckeVkM1jU.

Smile: upper lip ([email protected]):

c_33_smile_upper_lip

Age ([email protected]):

c_53_age

Look direction ([email protected]):

c_57_look_direction

Hair color ([email protected]):

c_08_hair_color

Left / right rotation ([email protected]):

c_03_left_right_rotation

Face oval: size ([email protected]):

c_16_face_oval_size

Hairstyle: background size ([email protected]):

c_24_hairstyle_background_size

Lower jaw size ([email protected]):

c_32_lower_jaw_size

Forward / backward inclination ([email protected]):

c_43_forward_backward_inclination

Mouth: open / closed ([email protected]):

c_44_mouth_open_closed

Hair: wavy / straight ([email protected]):

c_45_hair_curly_straight

Eyebrows: up / down ([email protected]):

c_48_eyebrows_up_down

Nose length ([email protected]):

c_49_nose_length

Nose: upturned tip ([email protected]):

c_52_nose_upturned_tip

Eyebrows shape ([email protected]):

c_55_eyebrows_shape

Vertical face stretch ([email protected]):

c_60_vertical_face_stretch

Color of the irises ([email protected]):

c_64_color_of_the_irises

Shape of the nostrils ([email protected]):

c_67_shape_of_the_nostrils

Hair texture ([email protected]):

c_68_hair_texture

Lower eyelid ([email protected]):

c_72_lower_eyelid

Wrinkles ([email protected]):

c_75_wrinkles

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].