simontomaskarlsson / Gan Mri
Licence: gpl-3.0
Code repository for Frontiers article 'Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT'
Stars: ✭ 159
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Gan Mri
Pytorch Cyclegan
A clean and readable Pytorch implementation of CycleGAN
Stars: ✭ 558 (+250.94%)
Mutual labels: cyclegan, image-processing
Cyclegan Qp
Official PyTorch implementation of "Artist Style Transfer Via Quadratic Potential"
Stars: ✭ 59 (-62.89%)
Mutual labels: neural-networks, cyclegan
Segmentation models.pytorch
Segmentation models with pretrained backbones. PyTorch.
Stars: ✭ 4,584 (+2783.02%)
Mutual labels: neural-networks, image-processing
Discogan Tensorflow
An implementation of DiscoGAN in tensorflow
Stars: ✭ 82 (-48.43%)
Mutual labels: neural-networks, generative-adversarial-networks
Artificio
Deep Learning Computer Vision Algorithms for Real-World Use
Stars: ✭ 326 (+105.03%)
Mutual labels: neural-networks, image-processing
Keras Gan
Keras implementations of Generative Adversarial Networks.
Stars: ✭ 8,494 (+5242.14%)
Mutual labels: neural-networks, generative-adversarial-networks
Cyclegan
PyTorch implementation of CycleGAN
Stars: ✭ 38 (-76.1%)
Mutual labels: generative-adversarial-networks, cyclegan
Kaggle Rsna
Deep Learning for Automatic Pneumonia Detection, RSNA challenge
Stars: ✭ 74 (-53.46%)
Mutual labels: neural-networks, image-processing
Torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
Stars: ✭ 1,156 (+627.04%)
Mutual labels: neural-networks, generative-adversarial-networks
Pix2depth
DEPRECATED: Depth Map Estimation from Monocular Images
Stars: ✭ 293 (+84.28%)
Mutual labels: neural-networks, cyclegan
Dped
Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks
Stars: ✭ 1,315 (+727.04%)
Mutual labels: generative-adversarial-networks, image-processing
Repo 2018
Deep Learning Summer School + Tensorflow + OpenCV cascade training + YOLO + COCO + CycleGAN + AWS EC2 Setup + AWS IoT Project + AWS SageMaker + AWS API Gateway + Raspberry Pi3 Ubuntu Core
Stars: ✭ 163 (+2.52%)
Mutual labels: generative-adversarial-networks, cyclegan
Cyclegan
Tensorflow implementation of CycleGAN
Stars: ✭ 348 (+118.87%)
Mutual labels: neural-networks, cyclegan
Fft Conv Pytorch
Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
Stars: ✭ 65 (-59.12%)
Mutual labels: neural-networks, image-processing
Awesome Medical Imaging
Awesome list of software that I use to do research in medical imaging.
Stars: ✭ 87 (-45.28%)
Mutual labels: neural-networks, image-processing
Cyclegan Keras
Keras implementation of CycleGAN using a tensorflow backend.
Stars: ✭ 152 (-4.4%)
Mutual labels: cyclegan, image-processing
Gpuimage X
A Cross-platform (for both Android & iOS) Framework for GPU-based Filters, Video and Image Processing.
Stars: ✭ 154 (-3.14%)
Mutual labels: image-processing
Gasyori100knock
image processing codes to understand algorithm
Stars: ✭ 1,988 (+1150.31%)
Mutual labels: image-processing
Zi2zi
Learning Chinese Character style with conditional GAN
Stars: ✭ 1,988 (+1150.31%)
Mutual labels: generative-adversarial-networks
Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT
[Arxiv paper]
Code usage
- Prepare your dataset under the directory 'data' in the CycleGAN or UNIT folder and set dataset name to parameter 'image_folder' in model init function.
- Directory structure on new dataset needed for training and testing:
- data/Dataset-name/trainA
- data/Dataset-name/trainB
- data/Dataset-name/testA
- data/Dataset-name/testB
- Train a model by:
python CycleGAN.py
or
python UNIT.py
- Generate synthetic images by following specifications under:
- CycleGAN/generate_images/ReadMe.md
- UNIT/generate_images/ReadMe.md
Result GIFs - 304x256 pixel images
Left: Input image. Middle: Synthetic images generated during training. Right: Ground truth.
Histograms show pixel value distributions for synthetic images (blue) compared to ground truth (brown).
(An updated image normalization, present in the current version of this repo, has fixed the intensity error seen in these results.)
CycleGAN - T1 to T2
CycleGAN - T2 to T1
UNIT - T1 to T2
UNIT - T2 to T1
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].