提交 49c32f44 编写于 作者: W WenmuZhou

change v1.1 to v2.0

上级 8d113f7d
...@@ -10,8 +10,8 @@ ...@@ -10,8 +10,8 @@
## 配置文件参数介绍 ## 配置文件参数介绍
`rec_chinese_lite_train_v1.1.yml ` 为例 `rec_chinese_lite_train_v2.0.yml ` 为例
### Global ### Global
| 字段 | 用途 | 默认值 | 备注 | | 字段 | 用途 | 默认值 | 备注 |
| :----------------------: | :---------------------: | :--------------: | :--------------------: | | :----------------------: | :---------------------: | :--------------: | :--------------------: |
...@@ -119,4 +119,4 @@ ...@@ -119,4 +119,4 @@
| shuffle | 每个epoch是否将数据集顺序打乱 | True | \ | | shuffle | 每个epoch是否将数据集顺序打乱 | True | \ |
| batch_size_per_card | 训练时单卡batch size | 256 | \ | | batch_size_per_card | 训练时单卡batch size | 256 | \ |
| drop_last | 是否丢弃因数据集样本数不能被 batch_size 整除而产生的最后一个不完整的mini-batch | True | \ | | drop_last | 是否丢弃因数据集样本数不能被 batch_size 整除而产生的最后一个不完整的mini-batch | True | \ |
| num_workers | 用于加载数据的子进程个数,若为0即为不开启子进程,在主进程中进行数据加载 | 8 | \ | | num_workers | 用于加载数据的子进程个数,若为0即为不开启子进程,在主进程中进行数据加载 | 8 | \ |
\ No newline at end of file
...@@ -9,8 +9,8 @@ The following list can be viewed through `--help` ...@@ -9,8 +9,8 @@ The following list can be viewed through `--help`
## INTRODUCTION TO GLOBAL PARAMETERS OF CONFIGURATION FILE ## INTRODUCTION TO GLOBAL PARAMETERS OF CONFIGURATION FILE
Take rec_chinese_lite_train_v1.1.yml as an example Take rec_chinese_lite_train_v2.0.yml as an example
### Global ### Global
| Parameter | Use | Defaults | Note | | Parameter | Use | Defaults | Note |
| :----------------------: | :---------------------: | :--------------: | :--------------------: | | :----------------------: | :---------------------: | :--------------: | :--------------------: |
...@@ -118,4 +118,4 @@ In ppocr, the network is divided into four stages: Transform, Backbone, Neck and ...@@ -118,4 +118,4 @@ In ppocr, the network is divided into four stages: Transform, Backbone, Neck and
| shuffle | Does each epoch disrupt the order of the data set | True | \ | | shuffle | Does each epoch disrupt the order of the data set | True | \ |
| batch_size_per_card | Single card batch size during training | 256 | \ | | batch_size_per_card | Single card batch size during training | 256 | \ |
| drop_last | Whether to discard the last incomplete mini-batch because the number of samples in the data set cannot be divisible by batch_size | True | \ | | drop_last | Whether to discard the last incomplete mini-batch because the number of samples in the data set cannot be divisible by batch_size | True | \ |
| num_workers | The number of sub-processes used to load data, if it is 0, the sub-process is not started, and the data is loaded in the main process | 8 | \ | | num_workers | The number of sub-processes used to load data, if it is 0, the sub-process is not started, and the data is loaded in the main process | 8 | \ |
\ No newline at end of file
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册