pix2pix
pix2pix copied to clipboard
Image-to-image translation with conditional adversarial nets
Decent results require 3k-5k frames. My GPU session on colab gets disconnected due to usage while training. I am saving the checkpoints in the drive. Is there any way I...
hi i want to generate paired images on my own dataset. After combining both A and B datasets, how to train and test, as i could find any training and...
Hi I am an architect and I want to examine ML for floorplan design - in fact I am writing a Masterthesis about the topic. I want to try pix2pix...
Hello, can you provide the dataset of Paris Street View,thanks
I find it an inconvenience to have to stitch together a fake 'B' image, when testing. I have noticed that if i provide the model with a 256x256 image (instead...
Hi everyone, I would like to implement the section of [evaluating labels2photos-on-cityscapes](https://github.com/phillipi/pix2pix#evaluating-labels2photos-on-cityscapes). But got very confused of what are the --cityscapes_dir, --result_dir, --output_dir What I have now: --cityscapes_dir: original cityscape...
I have a data set of paired images where the source image is a side or frontal view of a face and the target image is the exact same picture...
I'm confused how the evaluate.py works. I trained my own model with cityscapes dataset and want to conpare it with pix2pix using evaluate.py Here are 2 parameters I don't understand,...
Can I load the pre-trained mode for my owe training. And my owe dataset is different from the dataset which trained the pre-trained mode.