Skip to content

GitLab

Commit 468f84fd authored by chenzk's avatar chenzk
Browse files

Update url.md

parent 0d4eab47
Hide whitespace changes
Inline Side-by-side
Showing with 6 additions and 6 deletions
README.md
View file @ 468f84fd
......@@ -70,9 +70,9 @@ python setup.py develop
### 准备数据集
所需数据集为: DF2K(DIV2K和Flickr2K) + OST，仅需要**HR**图片.
[DIV2K](http://113.200.138.88:18080/aidatasets/project-dependency/div2k/-/blob/master/DIV2K_train_HR.zip)
[DIV2K](https://huggingface.co/datasets/goodfellowliu/DIV2K)
[Flickr2K](http://113.200.138.88:18080/aidatasets/project-dependency/flickr2k/-/blob/master/Flickr2K.tar)
[Flickr2K](https://huggingface.co/datasets/goodfellowliu/Flickr2K)
[OST](https://openmmlab.oss-cn-hangzhou.aliyuncs.com/datasets/OST_dataset.zip)
......@@ -150,7 +150,7 @@ python scripts/generate_meta_info.py --input datasets/DF2K/DF2K_HR，datasets/DF
2. [训练Real-ESRGAN](#训练Real-ESRGAN)
#### 训练Real-ESRNet
1. 下载预训练模型[ESRGAN](http://113.200.138.88:18080/aimodels/findsource-dependency/real-esrgan_pytorch/-/blob/main/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/v0.1.0/RealESRGAN_x4plus.pth)，将模型放到`experiments/pretrained_models`目录下。
2. 相应地修改`options/train_realesrnet_x4plus.yml`中的内容:
```yml
......@@ -205,7 +205,7 @@ train:
#### 动态生成降级图像
只需要高分辨率图像，在训练过程中，使用`Real-ESRGAN`描述的降级模型生成低质量图像。
1. 下载预训练模型[RealESRGAN_x4plus.pth](http://113.200.138.88:18080/aimodels/findsource-dependency/real-esrgan_pytorch/-/blob/main/RealESRGAN_x4plus.pth)、[RealESRGAN_x4plus_netD.pth](http://113.200.138.88:18080/aimodels/findsource-dependency/real-esrgan_pytorch/-/blob/main/RealESRGAN_x4plus_netD.pth)到`experiments/pretrained_models`目录下；
1. 下载预训练模型[RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)、[RealESRGAN_x4plus_netD.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth)到`experiments/pretrained_models`目录下，请根据源github说明文档地址下载；
2. 修改选项文件 [options/finetune_realesrgan_x4plus.yml](options/finetune_realesrgan_x4plus.yml)，特别是`datasets`部分：
......@@ -235,7 +235,7 @@ train:
python scripts/generate_meta_info_pairdata.py --input datasets/DF2K/DIV2K_train_HR_sub datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub --meta_info datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt
```
2. 下载所需预训练模型[RealESRGAN_x4plus.pth](http://113.200.138.88:18080/aimodels/findsource-dependency/real-esrgan_pytorch/-/blob/main/RealESRGAN_x4plus.pth)、[RealESRGAN_x4plus_netD.pth](http://113.200.138.88:18080/aimodels/findsource-dependency/real-esrgan_pytorch/-/blob/main/RealESRGAN_x4plus_netD.pth)到`experiments/pretrained_models`目录下。
2. 下载预训练模型[RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)、[RealESRGAN_x4plus_netD.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth)到`experiments/pretrained_models`目录下，请根据源github说明文档地址下载；
3. 微调准备
......@@ -270,7 +270,7 @@ bash run_train_multi.sh
```
## 推理
下载预训练模型[RealESRGAN_x4plus.pth](http://113.200.138.88:18080/aimodels/findsource-dependency/real-esrgan_pytorch/-/blob/main/RealESRGAN_x4plus.pth)，将其放入`weights`文件夹下，测试结果默认保存在`results`文件夹下。
下载预训练模型[RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)，将其放入`weights`文件夹下，测试结果默认保存在`results`文件夹下。
```bash
# 执行推理
......
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