From 277fd2f74a8661bff7e6a284c903e01988e3aac9 Mon Sep 17 00:00:00 2001 From: William Falcon Date: Tue, 19 Nov 2019 11:13:59 -0800 Subject: [PATCH] Update README.md --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 1b63fc0d15..832e42bd74 100644 --- a/README.md +++ b/README.md @@ -66,7 +66,9 @@ Lightning sets up all the boilerplate state-of-the-art training for you so you c --- ## How do I do use it? -Think about Lightning as refactoring your research code instead of using a new framework. The research code goes into a [LightningModule](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/) which you fit using a Trainer. +Think about Lightning as refactoring your research code instead of using a new framework. The research code goes into a [LightningModule](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/) which you fit using a Trainer. + +[Try this live demo on colab!](https://colab.research.google.com/drive/1F_RNcHzTfFuQf-LeKvSlud6x7jXYkG31#scrollTo=HOk9c4_35FKg) The LightningModule defines a *system* such as seq-2-seq, GAN, etc... It can ALSO define a simple classifier such as the example below.