Update: Modify test error.

README.md

@@ -106,32 +106,32 @@ We named this project IDDM: Industrial Defect Diffusion Model. It aims to reprod
 
 #### Normal Training
 
-1. Take the `landscape` dataset as an example and place the dataset files in the `datasets` folder. The overall path of the dataset should be `/your/path/datasets/landscape`, and the image files should be located at `/your/path/datasets/landscape/*.jpg`.
+1. Take the `landscape` dataset as an example and place the dataset files in the `datasets` folder. The overall path of the dataset should be `/your/path/datasets/landscape`, the images path should be `/your/path/datasets/landscape/images`, and the image files should be located at `/your/path/datasets/landscape/images/*.jpg`.
 
 2. Open the `train.py` file and locate the `--dataset_path` parameter. Modify the path in the parameter to the overall dataset path, for example, `/your/path/datasets/landscape`.
 
 3. Set the necessary parameters such as `--sample`, `--conditional`, `--run_name`, `--epochs`, `--batch_size`, `--image_size`, `--result_path`, etc. If no parameters are set, the default settings will be used. There are two ways to set the parameters: directly modify the `parser` in the `if __name__ == "__main__":` section of the `train.py` file (**WE RECOMMEND THIS WAY**), or run the following command in the terminal at the `/your/path/Defect-Diffusion-Model/tools` directory:  
    **Conditional Training Command**
 
    ```bash
-   python train.py --sample 'ddpm' --conditional True --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path '/your/dataset/path' --result_path '/your/save/path'
+   python train.py --sample ddpm --conditional True --run_name df --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path /your/dataset/path --result_path /your/save/path
    ```
    **Unconditional Training Command**
 
    ```bash
-   python train.py --sample 'ddpm' --conditional False --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --dataset_path '/your/dataset/path' --result_path '/your/save/path'
+   python train.py --sample ddpm --conditional False --run_name df --epochs 300 --batch_size 16 --image_size 64 --dataset_path /your/dataset/path --result_path /your/save/path
    ```
 4. Wait for the training to complete.
 5. If the training is interrupted due to any reason, you can resume it by setting `--resume` to `True` in the `train.py` file, specifying the epoch number where the interruption occurred, providing the folder name of the interrupted training (`run_name`), and running the file again. Alternatively, you can use the following command to resume the training:  
    **Conditional Resume Training Command**
 
    ```bash
-   python train.py --resume True --start_epoch 10 --load_model_dir 'df' --sample 'ddpm' --conditional True --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path '/your/dataset/path' --result_path '/your/save/path'
+   python train.py --resume True --start_epoch 10 --load_model_dir df --sample ddpm --conditional True --run_name df --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path /your/dataset/path --result_path /your/save/path
    ```
    **Unconditional Resume Training Command**
 
    ```bash
-   python train.py --resume True --start_epoch 10 --load_model_dir 'df' --sample 'ddpm' --conditional False --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --dataset_path '/your/dataset/path' --result_path '/your/save/path'
+   python train.py --resume True --start_epoch 10 --load_model_dir df --sample ddpm --conditional False --run_name df --epochs 300 --batch_size 16 --image_size 64 --dataset_path /your/dataset/path --result_path /your/save/path
    ```
 #### Distributed Training
 
@@ -144,13 +144,13 @@ We named this project IDDM: Industrial Defect Diffusion Model. It aims to reprod
    **Conditional Distributed Training Command**
 
    ```bash
-   python train.py --sample 'ddpm' --conditional True --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path '/your/dataset/path' --result_path '/your/save/path' --distributed True --main_gpu 0 --world_size 2
+   python train.py --sample ddpm --conditional True --run_name df --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path /your/dataset/path --result_path /your/save/path --distributed True --main_gpu 0 --world_size 2
    ```
 
    **Unconditional Distributed Training Command**
 
    ```bash
-   python train.py --sample 'ddpm' --conditional False --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --dataset_path '/your/dataset/path' --result_path '/your/save/path' --distributed True --main_gpu 0 --world_size 2
+   python train.py --sample ddpm --conditional False --run_name df --epochs 300 --batch_size 16 --image_size 64 --dataset_path /your/dataset/path --result_path /your/save/path --distributed True --main_gpu 0 --world_size 2
    ```
 
 4. Wait for the training to complete. Interrupt recovery is the same as basic training.
@@ -175,7 +175,7 @@ We named this project IDDM: Industrial Defect Diffusion Model. It aims to reprod
 | --fp16                 |             | Half precision training         | bool | Enable half precision training. It effectively reduces GPU memory usage but may affect training accuracy and results |
 | --optim                |             | Optimizer                       | str  | Optimizer selection. Currently supports Adam and AdamW       |
 | --act | | Activation function | str | Activation function selection. Currently supports gelu, silu, relu, relu6 and lrelu |
-| --lr                   |             | Learning rate                   | int  | Initial learning rate. Currently only supports linear learning rate |
+| --lr                   |             | Learning rate                   | float | Initial learning rate. Currently only supports linear learning rate |
 | --lr_func | | Learning rate schedule | str | Setting learning rate schedule, currently supporting linear, cosine, and warmup_cosine. |
 | --result_path          |             | Save path                       | str  | Path to save the training results                            |
 | --save_model_interval  |             | Save model after each training  | bool | Whether to save the model after each training iteration for model selection based on visualization |
@@ -200,13 +200,13 @@ We named this project IDDM: Industrial Defect Diffusion Model. It aims to reprod
    **Conditional Generation Command**
 
    ```bash
-   python generate.py --conditional True --generate_name 'df' --num_images 8 --num_classes 10 --class_name 0 --image_size 64 --weight_path '/your/path/weight/model.pt'
+   python generate.py --conditional True --generate_name df --num_images 8 --num_classes 10 --class_name 0 --image_size 64 --weight_path /your/path/weight/model.pt
    ```
 
    **Unconditional Generation Command**
 
    ```bash
-   python generate.py --conditional False --generate_name 'df' --num_images 8 --image_size 64 --weight_path '/your/path/weight/model.pt'
+   python generate.py --conditional False --generate_name df --num_images 8 --image_size 64 --weight_path /your/path/weight/model.pt
    ```
 
 3. Wait for the generation process to complete.

README_zh.md

@@ -85,7 +85,7 @@
 
    设置`--result_path`参数为`/你的/本地/或/远程服务器/文件/地址/results`；
 
-   设置`--num_classes`参数为`10`，这是你的类别总数；
+   设置`--num_classes`参数为`10`，这是你的类别总数）；
 
    设置更多参数（自定义），如果报`CUDA out of memory`错误，将`--batch_size`、`--num_workers`调小；
 
@@ -105,32 +105,32 @@
 
 #### 普通训练
 
-1. 以`landscape`数据集为例，将数据集文件放入`datasets`文件夹中，该数据集的总路径如下`/your/path/datasets/landscape`，数据集图片路径如下`/your/path/datasets/landscape/*.jpg`
+1. 以`landscape`数据集为例，将数据集文件放入`datasets`文件夹中，该数据集的总路径如下`/your/path/datasets/landscape`，图片存放在`/your/path/datasets/landscape/images`，数据集图片路径如下`/your/path/datasets/landscape/images/*.jpg`
 
 2. 打开`train.py`文件，找到`--dataset_path`参数，将参数中的路径修改为数据集的总路径，例如`/your/path/datasets/landscape`
 
 3. 设置必要参数，例如`--sample`，`--conditional`，`--run_name`，`--epochs`，`--batch_size`，`--image_size`，`--result_path`等参数，若不设置参数则使用默认设置。我们有两种参数设置方法，其一是直接对`train.py`文件`if __name__ == "__main__":`中的`parser`进行设置（**我们推荐这种方式**）；其二是在控制台在`/your/path/Defect-Diffiusion-Model/tools`路径下输入以下命令：
    **有条件训练命令**
 
    ```bash
-   python train.py --sample 'ddpm' --conditional True --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path '/your/dataset/path' --result_path '/your/save/path'
+   python train.py --sample ddpm --conditional True --run_name df --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path /your/dataset/path --result_path /your/save/path
    ```
    **无条件训练命令**
 
    ```bash
-   python train.py --sample 'ddpm' --conditional False --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --dataset_path '/your/dataset/path' --result_path '/your/save/path'
+   python train.py --sample ddpm --conditional False --run_name df --epochs 300 --batch_size 16 --image_size 64 --dataset_path /your/dataset/path --result_path /your/save/path
    ```
 4. 等待训练即可
 5. 若因异常原因中断训练，我们可以在`train.py`文件，首先将`--resume`设置为`True`，其次设置异常中断的迭代编号，再写入该次训练的所在文件夹（run_name），最后运行文件即可。也可以使用如下命令进行恢复：
    **有条件恢复训练命令**
 
    ```bash
-   python train.py --resume True --start_epoch 10 --load_model_dir 'df' --sample 'ddpm' --conditional True --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path '/your/dataset/path' --result_path '/your/save/path'
+   python train.py --resume True --start_epoch 10 --load_model_dir df --sample ddpm --conditional True --run_name df --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path /your/dataset/path --result_path /your/save/path
    ```
    **无条件恢复训练命令**
 
    ```bash
-   python train.py --resume True --start_epoch 10 --load_model_dir 'df' --sample 'ddpm' --conditional False --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --dataset_path '/your/dataset/path' --result_path '/your/save/path'
+   python train.py --resume True --start_epoch 10 --load_model_dir df --sample ddpm --conditional False --run_name df --epochs 300 --batch_size 16 --image_size 64 --dataset_path /your/dataset/path --result_path /your/save/path
    ```
 
 #### 分布式训练
@@ -144,13 +144,13 @@
    **有条件训练命令**
 
    ```bash
-   python train.py --sample 'ddpm' --conditional True --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path '/your/dataset/path' --result_path '/your/save/path' --distributed True --main_gpu 0 --world_size 2
+   python train.py --sample ddpm --conditional True --run_name df --epochs 300 --batch_size 16 --image_size 64 --num_classes 10 --dataset_path /your/dataset/path --result_path /your/save/path --distributed True --main_gpu 0 --world_size 2
    ```
 
    **无条件训练命令**
 
    ```bash
-   python train.py --sample 'ddpm' --conditional False --run_name 'df' --epochs 300 --batch_size 16 --image_size 64 --dataset_path '/your/dataset/path' --result_path '/your/save/path' --distributed True --main_gpu 0 --world_size 2
+   python train.py --sample ddpm --conditional False --run_name df --epochs 300 --batch_size 16 --image_size 64 --dataset_path /your/dataset/path --result_path /your/save/path --distributed True --main_gpu 0 --world_size 2
    ```
 
 3. 等待训练即可，中断恢复同基本训练一致。
@@ -178,7 +178,7 @@
 | --fp16                 |          | 半精度训练                       |   bool   | 开启半精度训练，有效减少显存使用，但无法保证训练精度和训练结果 |
 | --optim                |          | 优化器                           |   str    | 优化器选择，目前支持adam和adamw                              |
 | --act                  |          | 激活函数                         |   str    | 激活函数选择，目前支持gelu、silu、relu、relu6和lrelu         |
-| --lr                   |          | 学习率                           |   int    | 初始化学习率，目前仅支持线性学习率                           |
+| --lr                   |          | 学习率                           |  float   | 初始化学习率，目前仅支持线性学习率                           |
 | --lr_func              |          | 学习率方法                       |   str    | 设置学习率方法，当前支持linear、cosine和warmup_cosine        |
 | --result_path          |          | 保存路径                         |   str    | 保存路径                                                     |
 | --save_model_interval  |          | 是否每次训练储存                 |   bool   | 是否每次训练储存，根据可视化生成样本信息筛选模型             |
@@ -205,13 +205,13 @@
    **有条件生成命令**
 
    ```bash
-   python generate.py --conditional True --generate_name 'df' --num_images 8 --num_classes 10 --class_name 0 --image_size 64 --weight_path '/your/path/weight/model.pt'
+   python generate.py --conditional True --generate_name df --num_images 8 --num_classes 10 --class_name 0 --image_size 64 --weight_path /your/path/weight/model.pt
    ```
 
    **无条件生成命令**
 
    ```bash
-   python generate.py --conditional False --generate_name 'df' --num_images 8 --image_size 64 --weight_path '/your/path/weight/model.pt'
+   python generate.py --conditional False --generate_name df --num_images 8 --image_size 64 --weight_path /your/path/weight/model.pt
    ```
 
 3. 等待生成即可