taming-transformers
taming-transformers copied to clipboard
CompVis
Taming Transformers for High-Resolution Image Synthesis
Hi, Thanks for sharing this nice work! I have some questions about training details of VQGAN on ImageNet. - How many epochs should I train? - How many GPUs are...
Hi Team, After training vqgan model on custom data as per below steps: ---Put your image files in a folder custom_data folder ---Create 2 text files a xx_train.txt and xx_test.txt...
When I run it: RuntimeWarning: You are using LearningRateMonitor callback with models that have no learning rate schedulers. Please see documentation for `configure_optimizers` method. Can anyone tell me why this...
How do I sample after training a model on a custom dataset?
Hi, Thank you for your excellent work. I have a question regarding the embed_dim parameter. In all the configurations in this [repository](https://github.com/CompVis/taming-transformers/blob/3ba01b241669f5ade541ce990f7650a3b8f65318/configs/imagenet_vqgan.yaml#L5), the embed_dim is set to 256, which appears...
Due to recent changes in PyTorch, the original CompVis/taming-transformers repository requires small updates to remain compatible. In the file /traming-transformers/taming/data/utils.py, I have changed string_classes to str in line 152. After...
As `torch._six` is no longer available in recent PyTorch versions, this breaks the package when used with recent PyTorch installs. Alternatively, using `string_classes` containing the default Python `str` type fixes...
Hello, I have seen a lot of people having problems with the training on conditional. What I did that worked was to first preprocess the images correctly, they gave as...
cannot import name 'DDPPlugin' from 'pytorch_lightning.plugins' can anyone help me with this? ptl version 1.0.8 torch 1.7
