GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → LynnHo → Hd Celeba Cropper

LynnHo / Hd Celeba Cropper

Licence: mit
To obtain high resolution face images from CelebA

Programming Languages

python
139335 projects - #7 most used programming language

Labels

celeba

Projects that are alternatives of or similar to Hd Celeba Cropper

DCGAN-Pytorch
A Pytorch implementation of "Deep Convolutional Generative Adversarial Networks"
Stars: ✭ 23 (-81.75%)
Mutual labels:  celeba
Beta Vae
Pytorch implementation of β-VAE
Stars: ✭ 326 (+158.73%)
Mutual labels:  celeba
Celebamask Hq
A large-scale face dataset for face parsing, recognition, generation and editing.
Stars: ✭ 1,156 (+817.46%)
Mutual labels:  celeba
gan-error-avoidance
Learning to Avoid Errors in GANs by Input Space Manipulation (Code for paper)
Stars: ✭ 23 (-81.75%)
Mutual labels:  celeba
Alae
[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+2422.22%)
Mutual labels:  celeba
Pytorch Mnist Celeba Gan Dcgan
Pytorch implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Networks (DCGAN) for MNIST and CelebA datasets
Stars: ✭ 363 (+188.1%)
Mutual labels:  celeba
Infogan Pytorch
PyTorch Implementation of InfoGAN
Stars: ✭ 197 (+56.35%)
Mutual labels:  celeba
Tf Exercise Gan
Tensorflow implementation of different GANs and their comparisions
Stars: ✭ 110 (-12.7%)
Mutual labels:  celeba
Pytorch Mnist Celeba Cgan Cdcgan
Pytorch implementation of conditional Generative Adversarial Networks (cGAN) and conditional Deep Convolutional Generative Adversarial Networks (cDCGAN) for MNIST dataset
Stars: ✭ 290 (+130.16%)
Mutual labels:  celeba
Began Tensorflow
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"
Stars: ✭ 904 (+617.46%)
Mutual labels:  celeba
style-vae
Implementation of VAE and Style-GAN Architecture Achieving State of the Art Reconstruction
Stars: ✭ 25 (-80.16%)
Mutual labels:  celeba
DCGAN-CelebA-PyTorch-CPP
DCGAN Implementation using PyTorch in both C++ and Python
Stars: ✭ 14 (-88.89%)
Mutual labels:  celeba
Disentangling Vae
Experiments for understanding disentanglement in VAE latent representations
Stars: ✭ 398 (+215.87%)
Mutual labels:  celeba
cDCGAN
PyTorch implementation of Conditional Deep Convolutional Generative Adversarial Networks (cDCGAN)
Stars: ✭ 49 (-61.11%)
Mutual labels:  celeba
Celeba Hq Modified
Modified h5tool.py make user getting celeba-HQ easier
Stars: ✭ 84 (-33.33%)
Mutual labels:  celeba
Gan Tutorial
Simple Implementation of many GAN models with PyTorch.
Stars: ✭ 227 (+80.16%)
Mutual labels:  celeba
Pycadl
Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"
Stars: ✭ 356 (+182.54%)
Mutual labels:  celeba
Msg Gan V1
MSG-GAN: Multi-Scale Gradients GAN (Architecture inspired from ProGAN but doesn't use layer-wise growing)
Stars: ✭ 116 (-7.94%)
Mutual labels:  celeba
Interpretability By Parts
Code repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)
Stars: ✭ 88 (-30.16%)
Mutual labels:  celeba
Tf.gans Comparison
Implementations of (theoretical) generative adversarial networks and comparison without cherry-picking
Stars: ✭ 477 (+278.57%)
Mutual labels:  celeba
View All Similar Projects ➔

HD CelebA Cropper

CelebA dataset provides an aligned set img_align_celeba.zip. However, the size of each aligned image is 218x178, so the faces cropped from such images would be even smaller!

Here we provide a code to obtain higher resolution face images, by cropping the faces from the original unaligned images via 68 landmarks.

We also use a deep image quality assessment method to evaluate and rank the cropped image quality in scores.txt, lower score the better.

Cropped Faces (512x512)

Notice: There are still some low resolution cropped faces since the corresponding original images are low resolution.

Usage

  • Prerequisites

    • OpenCV

    • Python 3.6

  • Dataset

    • CelebA-unaligned (10.2GB, higher quality than the aligned data)

      • download the dataset

      • unzip the data

        7z x ./data/img_celeba.7z/img_celeba.7z.001 -o./data/

unzip ./data/annotations.zip -d ./data/

  • Cropping Examples

    • 512x512 + lanczos4 + jpg

      python align.py --crop_size_h 512 --crop_size_w 512 --order 4 --save_format jpg --n_worker 32

    • 512x512 + lanczos4 + png + larger face in the image (by setting face_factor, default is 0.45)

      python align.py --crop_size_h 512 --crop_size_w 512 --order 4 --save_format png --face_factor 0.6 --n_worker 32

    • 384x384 + bicubic + jpg + smaller face in the image (by setting face_factor, default is 0.45)

      python align.py --crop_size_h 384 --crop_size_w 384 --order 3 --save_format jpg --face_factor 0.3 --n_worker 32

  • Notice

    • order

      • 0: INTER_NEAREST

      • 1: INTER_LINEAR

      • 2: INTER_AREA

      • 3: INTER_CUBIC

      • 4: INTER_LANCZOS4

      • 5: INTER_LANCZOS4

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].