How do we train cycada feature &pixel

[xiaoqianjia]

Hi Can you explain how do we train cycada pixel only, feature only, pixel & feature with GTA5 to CityScapes?
I am confused the results from ./train_fcn.sh ./train_fcn_adda.sh, what's the different between them?

Thanks

[jhoffman]

train_fcn.sh trains a semantic segmentation model using the ground truth labels (standard supervised learning). You should use this to pre-train your source model with known labels.

train_fcn_adda.sh uses the feature adaptation to update the source initialized model output from previous step according to optimizing with the unlabeled target data.

For GTA->CityScapes the procedure is:

1. Train CycleGAN based pixel adaptation to translate GTA images to resemble CityScapes images (or download the translated images directly from the provided link)
2. Run standard fcn training on the translated GTA images with the known GTA labels
3. Train feature space adaptation taking as input the translated GTA images, CityScapes images and the output weights from step 2

[JamesChenChina]

Do you know how to "Train CycleGAN based pixel adaptation to translate GTA images to resemble CityScapes images"? @xiaoqianjia
Many thanks

[JamesChenChina]

@jhoffman Do you have the pre-trained model for "Train CycleGAN based pixel adaptation to translate GTA images to resemble CityScapes images"?
Many thanks!

[Luodian]

@jhoffman Same question, how to translate GTA images to CityScapes images by our own?
I find it's different from Cyclegan's original code, especially in cycle_gan_semantic_models.py.

I set my dataset properly using 'unaligned_datasets.py', but when I run train.py in cyclegan module.

It raises an error about no self.input_A_label found.