mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00
Code Issues Projects Releases Wiki Activity

[Fix] fix the config name style description (#1414)

Browse Source
This commit is contained in:
Rockey 2022-03-24 14:57:20 +08:00 committed by GitHub
parent 0d51115d85
commit 01e35aa6f7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/en/tutorials/config.md
View File

@ -24,7 +24,7 @@ Please refer to [mmcv](https://mmcv.readthedocs.io/en/latest/understand_mmcv/con
We follow the below style to name config files. Contributors are advised to follow the same style. We follow the below style to name config files. Contributors are advised to follow the same style.
``` ```
{model}_{backbone}_[misc]_[gpu x batch_per_gpu]_{resolution}_{schedule}_{dataset} {model}_{backbone}_[misc]_[gpu x batch_per_gpu]_{resolution}_{iterations}_{dataset}
``` ```
`{xxx}` is required field and `[yyy]` is optional. `{xxx}` is required field and `[yyy]` is optional.
@ -33,7 +33,7 @@ We follow the below style to name config files. Contributors are advised to foll
- `{backbone}`: backbone type like `r50` (ResNet-50), `x101` (ResNeXt-101). - `{backbone}`: backbone type like `r50` (ResNet-50), `x101` (ResNeXt-101).
- `[misc]`: miscellaneous setting/plugins of model, e.g. `dconv`, `gcb`, `attention`, `mstrain`. - `[misc]`: miscellaneous setting/plugins of model, e.g. `dconv`, `gcb`, `attention`, `mstrain`.
- `[gpu x batch_per_gpu]`: GPUs and samples per GPU, `8x2` is used by default. - `[gpu x batch_per_gpu]`: GPUs and samples per GPU, `8x2` is used by default.
- `{schedule}`: training schedule, `20ki` means 20k iterations. - `{iterations}`: number of training iterations like `160k`.
- `{dataset}`: dataset like `cityscapes`, `voc12aug`, `ade`. - `{dataset}`: dataset like `cityscapes`, `voc12aug`, `ade`.
## An Example of PSPNet ## An Example of PSPNet

4
docs/zh_cn/tutorials/config.md
View File

@ -21,7 +21,7 @@
我们按照下面的风格去命名配置文件，社区贡献者被建议使用同样的风格。 我们按照下面的风格去命名配置文件，社区贡献者被建议使用同样的风格。
``` ```
{model}_{backbone}_[misc]_[gpu x batch_per_gpu]_{resolution}_{schedule}_{dataset} {model}_{backbone}_[misc]_[gpu x batch_per_gpu]_{resolution}_{iterations}_{dataset}
``` ```
`{xxx}` 是被要求的文件 `[yyy]` 是可选的。 `{xxx}` 是被要求的文件 `[yyy]` 是可选的。
@ -30,7 +30,7 @@
- `{backbone}`: 主干网络种类，例如 `r50` (ResNet-50)， `x101` (ResNeXt-101) - `{backbone}`: 主干网络种类，例如 `r50` (ResNet-50)， `x101` (ResNeXt-101)
- `[misc]`: 模型中各式各样的设置/插件，例如 `dconv`， `gcb`， `attention`， `mstrain` - `[misc]`: 模型中各式各样的设置/插件，例如 `dconv`， `gcb`， `attention`， `mstrain`
- `[gpu x batch_per_gpu]`: GPU数目 和每个 GPU 的样本数， 默认为 `8x2` - `[gpu x batch_per_gpu]`: GPU数目 和每个 GPU 的样本数， 默认为 `8x2`
- `{schedule}`: 训练方案， `20ki` 意思是 20k 迭代轮数 - `{iterations}`: 训练迭代轮数，如`160k`
- `{dataset}`: 数据集，如 `cityscapes`， `voc12aug`， `ade` - `{dataset}`: 数据集，如 `cityscapes`， `voc12aug`， `ade`
## PSPNet 的一个例子 ## PSPNet 的一个例子