custom dataset training

Author: pesser

README.md

@@ -15,6 +15,7 @@
 
 
 ### News
+- Thanks to [rom1504](https://github.com/rom1504) it is now easy to [train a VQGAN on your own datasets](#training-on-custom-data).
 - Included a bugfix for the quantizer. For backward compatibility it is
   disabled by default (which corresponds to always training with `beta=1.0`).
   Use `legacy=False` in the quantizer config to enable it.
@@ -186,9 +187,10 @@ Training on your own dataset can be beneficial to get better tokens and hence be
 Those are the steps to follow to make this work:
 1. install the repo with `conda env create -f environment.yaml`, `conda activate taming` and `pip install -e .`
 1. put your .jpg files in a folder `your_folder`
-2. create 2 text files a xx_train.txt and xx_test.txt that point to the files in your training and test set respectively (for example `find `pwd`/your_folder -name "*.jpg" > train.txt`)
-3. adapt configs/custom_vqgan.yaml to point to these 2 files
-4. run `python main.py --base configs/custom_vqgan.yaml -t True --gpus 0,1`
+2. create 2 text files a `xx_train.txt` and `xx_test.txt` that point to the files in your training and test set respectively (for example `find $(pwd)/your_folder -name "*.jpg" > train.txt`)
+3. adapt `configs/custom_vqgan.yaml` to point to these 2 files
+4. run `python main.py --base configs/custom_vqgan.yaml -t True --gpus 0,1` to
+   train on two GPUs. Use `--gpus 0,` (with a trailing comma) to train on a single GPU.
 
 ## Data Preparation