Skip to content
Snippets Groups Projects
Unverified Commit 4e5c40b5 authored by Zhengfei-0311's avatar Zhengfei-0311 Committed by GitHub
Browse files

[Doc]: Update config.md (#562)

* Update config.md

* Update config.md
parent a5eb1791
No related branches found
No related tags found
No related merge requests found
...@@ -113,7 +113,7 @@ optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001) ...@@ -113,7 +113,7 @@ optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
然后在算法库中可以通过如下代码构造优化器对象。 然后在算法库中可以通过如下代码构造优化器对象。
```python ```python
from mmengine import Config from mmengine import Config, optim
from mmengine.registry import OPTIMIZERS from mmengine.registry import OPTIMIZERS
import torch.nn as nn import torch.nn as nn
...@@ -573,7 +573,7 @@ MMEngine 还提供了 `get_config` 和 `get_model` 两个接口,支持对符 ...@@ -573,7 +573,7 @@ MMEngine 还提供了 `get_config` 和 `get_model` 两个接口,支持对符
用户可以通过指定 `pretrained=True` 获得已经加载预训练权重的模型以进行训练或者推理。 用户可以通过指定 `pretrained=True` 获得已经加载预训练权重的模型以进行训练或者推理。
```python ```python
from mmengine import get_model from mmengine.hub import get_model
model = get_model( model = get_model(
'mmdet::faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py', pretrained=True) 'mmdet::faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py', pretrained=True)
...@@ -590,7 +590,7 @@ http loads checkpoint from path: https://download.openmmlab.com/mmdetection/v2.0 ...@@ -590,7 +590,7 @@ http loads checkpoint from path: https://download.openmmlab.com/mmdetection/v2.0
同时,如果用户指定 `pretrained=True` ,得到的配置文件中会新增 `model_path` 字段,指定了对应模型预训练权重的路径。 同时,如果用户指定 `pretrained=True` ,得到的配置文件中会新增 `model_path` 字段,指定了对应模型预训练权重的路径。
```python ```python
from mmengine import get_config from mmengine.hub import get_config
cfg = get_config( cfg = get_config(
'mmdet::faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py', pretrained=True) 'mmdet::faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py', pretrained=True)
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment