pix2pix
pix2pix copied to clipboard
matlab-deep-learning
Image to Image Translation Using Generative Adversarial Networks
Hello, I am trying to reach the PSNR value in a paper by using your code and facades dataset. The paper reports the PSNR value as 24.966 dB with same...
I notice that one of the options is options.ResumeFrom which makes me think that we can train the network for say 100 epochs and test it, and then save it...
Hello, First of all thanks for the code! I trained a model. It is quite big in size (600MB). Is there a way to make it more compact? In normal...
This is really helpful code and very good documentation on how to use it. I just have one small question. I trained the network on some images (I used just...
Is it possible to use multiple images as input for this code? The temporal information between images are needed in my work, thanks in advance.
exportONNXNetwork() doesn't support dlnetwork object. Is there a way to export the trained dlnetwork object to onnx for further deployment to other frameworks/production?
"Once the model is trained we can use the generator to make generate a new image." Should be: "Once the model is trained we can use the generator to generate...
An easy gotcha is to train a model with ARange set to a non-default value, then forget to set this same value when using `p2p.translate` (as mentioned in #4). Saving...
Hi, I am trying to use a six-channel image; the output is only a three-channel image. I added a quick fix to the training method to let me concatenate the...
Dear Author, the previewed 9-cell prediction results during model training are good, but the results for the prediction of images using the translate module are very poor. I would like...
Metadata
Owner
Metadata
Image to Image Translation Using Generative Adversarial Networks