Commit 91d9e772 authored by Rayyyyy's avatar Rayyyyy
Browse files

update README

parent f715b2c2
...@@ -41,7 +41,6 @@ docker build --no-cache -t hat:latest . ...@@ -41,7 +41,6 @@ docker build --no-cache -t hat:latest .
docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/ --shm-size=32G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/ --shm-size=32G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
cd /your_code_path/hat_pytorch cd /your_code_path/hat_pytorch
pip install -r requirements.txt
python setup.py develop python setup.py develop
``` ```
...@@ -111,7 +110,7 @@ python extract_subimages.py # 将图片进行sub ...@@ -111,7 +110,7 @@ python extract_subimages.py # 将图片进行sub
3. 生成 meta_info_file 3. 生成 meta_info_file
```bash ```bash
python scripts/data_preparation/generate_meta_info.py python generate_meta_info.py
``` ```
## 训练 ## 训练
...@@ -122,6 +121,7 @@ python scripts/data_preparation/generate_meta_info.py ...@@ -122,6 +121,7 @@ python scripts/data_preparation/generate_meta_info.py
### 单机多卡 ### 单机多卡
```bash ```bash
# 默认 train_HAT_SRx4_finetune_from_ImageNet_pretrain.yml
bash train.sh bash train.sh
``` ```
...@@ -134,6 +134,7 @@ bash train.sh ...@@ -134,6 +134,7 @@ bash train.sh
执行命令如下, 训练日志保存在logs文件夹下 执行命令如下, 训练日志保存在logs文件夹下
```bash ```bash
# 默认 train_HAT_SRx4_finetune_from_ImageNet_pretrain.yml
bash run_train_multi.sh bash run_train_multi.sh
``` ```
...@@ -142,6 +143,7 @@ bash run_train_multi.sh ...@@ -142,6 +143,7 @@ bash run_train_multi.sh
测试结果将保存到 ./results 路径下。options/test/HAT_SRx4_ImageNet-LR.yml 适用于不使用 ground truth image 的推理过程。 测试结果将保存到 ./results 路径下。options/test/HAT_SRx4_ImageNet-LR.yml 适用于不使用 ground truth image 的推理过程。
```bash ```bash
# 默认 HAT_SRx4_ImageNet-pretrain.yml
bash val.sh bash val.sh
``` ```
......
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