From e9d713a486b2201c5b82eb4c1fc099ddce6e24c6 Mon Sep 17 00:00:00 2001
From: Benjamin Gregg <90132896+Night1099@users.noreply.github.com>
Date: Sat, 25 May 2024 20:29:44 -0700
Subject: [PATCH] Update README.md

---
 README.md | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index dc1756f..92d911f 100644
--- a/README.md
+++ b/README.md
@@ -21,9 +21,12 @@ Python 3.8.8 and Pytorch 2.0.1. Details can be found in `requirements.txt`.
 
 1.2 Combine the HR images from these two datasets in `your_data_path/DF2K/HR` to build the DF2K dataset. 
 
-### 2. Begin to train
+### 2. Resume training from pretrained model
 Run `python main.py` to train on the DF2K dataset. Please update `dir_data` in the bash file as `your_data_path`.
 
+### 3. Start training from scratch
+Run `python main.py --start_epoch 0` to train on the DF2K dataset. Please update `dir_data` in the bash file as `your_data_path`.
+
 ## Test
 ### 1. Prepare test data 
 Download [benchmark datasets](https://github.com/xinntao/BasicSR/blob/a19aac61b277f64be050cef7fe578a121d944a0e/docs/Datasets.md) (e.g., Set5, Set14 and other test sets) and prepare HR/LR images in `your_data_path/benchmark`.