Patrick Esser

Hi @Johnson-yue , Thanks for your message. The workflow you described is only applicable in the case where you have paired training data (as in the super-resolution example). Unpaired translation...

Hi westream, are you asking if the `[configs/project.yaml]` part should be removed? It is only needed if you want to log to [Weights & Biases](https://app.wandb.ai/), otherwise you can just remove...

It's included in the transformer checkpoint. If you want to extract it, run ``` python scripts/extract_submodel.py logs/2021-01-20T16-04-20_coco_transformer/checkpoints/last.ckpt coco_cond_stage.ckpt cond_stage_model ```

Added config and loss to train cond stage on segmentation maps (`configs/coco_cond_stage.yaml` and `configs/sflckr_cond_stage.yaml`). Optionally, you can also extract weights of cond stage from the transformer checkpoints, ``` python scripts/extract_submodel.py...

The colors are actually just chosen randomly (you can see it either in the `show_segmentation` function defined in the notebook, or [here](https://github.com/CompVis/taming-transformers/blob/bced2865810fcd0d03f49d228d8922fc67f8c094/taming/models/vqgan.py#L146)). The model itself uses a one-hot encoding of...

Hi, Since we are using edflow extensively for our projects, we cannot provide a standalone version. However, if you are encountering a specific problem with it, we'd be happy to...

See tensorflow/tensorflow#12598

will be fixed once afd50b3fc12fad9c9eebb5a4ca06fb89bdac35f7 is merged. It's already in the `bleeding` branch if you need it.

#217 switched eval pipeline to MetaDataset. Next up: resurrect `edcache` with MetaDataset.

+1 for checkpoint abstraction!