"examples/vscode:/vscode.git/clone" did not exist on "e6ef08f367e0389e811d63eaa5afb16183a19e2b"
Commit 3799d625 authored by Rayyyyy's avatar Rayyyyy
Browse files

update readme

parent 5e83dadf
...@@ -152,6 +152,11 @@ python scripts/generate_meta_info.py --input datasets/DF2K/DF2K_HR, datasets/DF2 ...@@ -152,6 +152,11 @@ python scripts/generate_meta_info.py --input datasets/DF2K/DF2K_HR, datasets/DF2
## 训练 ## 训练
### 完整训练 ### 完整训练
完整训练分为两步,第一步训练得到Real-ESRNet, 在Real-ESRNet的基础上训练得到Real-ESRGAN。
1. [训练Real-ESRNet](#训练Real-ESRNet)
2. [训练Real-ESRGAN](#训练Real-ESRGAN)
#### 训练Real-ESRNet #### 训练Real-ESRNet
1. 下载预训练模型 [ESRGAN](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth), 将模型放到 `experiments/pretrained_models`目录下。 1. 下载预训练模型 [ESRGAN](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth), 将模型放到 `experiments/pretrained_models`目录下。
```bash ```bash
......
...@@ -9,6 +9,7 @@ echo "Training start ..." ...@@ -9,6 +9,7 @@ echo "Training start ..."
# python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume # python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume
## single ## single
# python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --auto_resume # python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --auto_resume
## Train Real-ESRGAN ## Train Real-ESRGAN
# python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume # python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume
## single ## single
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment