“24509f4af942bb250564756ad636691c7921e1df”上不存在“python/paddle/fluid/distribute_transpiler_simple.py”
未验证 提交 14139f8f 编写于 作者: J jerrywgz 提交者: GitHub

refine README (#1355)

* refine README
上级 6095dd07
...@@ -57,6 +57,7 @@ After data preparation, one can start the training step by: ...@@ -57,6 +57,7 @@ After data preparation, one can start the training step by:
sh ./pretrained/download.sh sh ./pretrained/download.sh
Set `pretrained_model` to load pre-trained model. In addition, this parameter is used to load trained model when finetuning as well. Set `pretrained_model` to load pre-trained model. In addition, this parameter is used to load trained model when finetuning as well.
Please make sure that pretrained_model is downloaded and loaded correctly, otherwise, the loss may be NAN during training.
**Install the [cocoapi](https://github.com/cocodataset/cocoapi):** **Install the [cocoapi](https://github.com/cocodataset/cocoapi):**
......
...@@ -57,6 +57,7 @@ Faster RCNN 目标检测模型 ...@@ -57,6 +57,7 @@ Faster RCNN 目标检测模型
sh ./pretrained/download.sh sh ./pretrained/download.sh
通过初始化`pretrained_model` 加载预训练模型。同时在参数微调时也采用该设置加载已训练模型。 通过初始化`pretrained_model` 加载预训练模型。同时在参数微调时也采用该设置加载已训练模型。
请在训练前确认预训练模型下载与加载正确,否则训练过程中损失可能会出现NAN。
**安装[cocoapi](https://github.com/cocodataset/cocoapi):** **安装[cocoapi](https://github.com/cocodataset/cocoapi):**
......
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