From 14139f8fad9f3faeec67b8b3823e63531f9318d5 Mon Sep 17 00:00:00 2001 From: jerrywgz Date: Wed, 17 Oct 2018 10:33:40 +0800 Subject: [PATCH] refine README (#1355) * refine README --- fluid/faster_rcnn/README.md | 1 + fluid/faster_rcnn/README_cn.md | 1 + 2 files changed, 2 insertions(+) diff --git a/fluid/faster_rcnn/README.md b/fluid/faster_rcnn/README.md index 617a1032..b676cce6 100644 --- a/fluid/faster_rcnn/README.md +++ b/fluid/faster_rcnn/README.md @@ -57,6 +57,7 @@ After data preparation, one can start the training step by: 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. +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):** diff --git a/fluid/faster_rcnn/README_cn.md b/fluid/faster_rcnn/README_cn.md index 6f9e892e..b17386a9 100644 --- a/fluid/faster_rcnn/README_cn.md +++ b/fluid/faster_rcnn/README_cn.md @@ -57,6 +57,7 @@ Faster RCNN 目标检测模型 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。 +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)：** -- GitLab