Open
Conversation
1. pix2pix now uses hyperparameter lambda_L1, instead of lambda_A, and its value defaults to 100.0 following Isola et al. 2. Model-specific options, such as lambda_A or lambda_L1 are now configured in each model file. 3. The default value for the common options can now change depending on model name. For example, dataset_mode defaults to 'unaligned' for --model cycle_gan, but it defaults to 'aligned' for --model pix2pix. 4. option now also displays the default value if not equal to the default. 5. addded a test script to test this.
…tion. Please see data/__init__.py 2. The default options are overwritable by each dataset, although the current datasets are not using them. 3. [none] option was explicitly added to --resize_or_crop option. The image sizes are still adjusted to multiples of 4. 4. better visdom error display 5. pix2pix_model now sets more default values
…f the model file name
Fix the error doc string in the data init helper function
…and-pix2pix Conflicts: README.md
These files were changed since the commit 568ad02. e
Update q and a
Create random wgangp alpha directly on device
Added Citation link for the Facades dataset
Colab quickstarts for CycleGAN and Pix2Pix
Owner
|
Could you git pull the latest code, and then make your commit? |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
18 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
i face the error of array broadcasting (2,3)->(2,2) i solved it with :
import skimage.io
import skimage.color
line#60 in script: image=skimage.io.imread(os.path.join(args.images_dir, imgList[i]))
if image.ndim!=3:
image=skimage.color.gray2rgb(image)
#for alpha channel
if image.shape[-1]==4:
image=image[..., :3]