pix2pix is a deep-learning method that can be used to translate one type of images into another. While pix2pix can potentially be used for any type of image-to-image translation, we demonstrate that it can be used to predict a fluorescent image from another fluorescent image.

Our pix2pix notebook is based on the following paper:

• Image-to-Image Translation with Conditional Adversarial Networks

• The source code of the PyTorch implementation of pix2pix can be found here: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix

Please also cite this original paper when using or developing our notebook.

For pix2pix to train, it needs to have access to a paired training dataset. This means that the same image needs to be acquired in the two conditions and provided with an indication of correspondence. Therefore, the data structure is important. It is necessary that all the input data are in the same folder and that all the output data is in a separate folder. The provided training dataset is already split in two folders called Training_source and Training_target.

• We strongly recommend that you generate extra paired images. These images can be used to assess the quality of your trained model (Quality control dataset). The quality control assessment can be done directly in the pix2pix notebook.

• Additionally, the corresponding input and output files need to have the same name.

• Please note that you currently can only use RGB .PNG files!

Coming soon...

Network	Link to example training and test dataset	Direct link to notebook in Colab
pix2pix	here

or:

To train pix2pix in Google Colab:

• Download our streamlined ZeroCostDL4Mic notebooks

• Open Google Colab

• Once the notebook is open, follow the instructions.