pytorch-layoutnet
pytorch-layoutnet copied to clipboard
How to downsize the model
My current laptop has a 4 GB graphics card due to which I am unable to train the model on it. Can you please tell me how should I go about making the changes in order to run it on my machine. Thank you!
You can just modified the model.py
to reduce the size of the model.
For example: reducing the numbers of channels, remove few layers of the encoder/decoder...
This path Downsize-channels.patch.txt divide the numbers of channels of each layers for you and take less than 3G gpu on my machine while training.
Hope it helps you.
This works perfectly. Thank you so much.