From 9be9eb7e2e2751a2a67389cda3112d64a01b217f Mon Sep 17 00:00:00 2001 From: qingqing01 Date: Tue, 30 Oct 2018 16:43:21 +0800 Subject: [PATCH] Update v2 VGG model URL. (#1411) --- legacy/ssd/README.cn.md | 2 +- legacy/ssd/README.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/legacy/ssd/README.cn.md b/legacy/ssd/README.cn.md index 2e510908..f9dbde50 100644 --- a/legacy/ssd/README.cn.md +++ b/legacy/ssd/README.cn.md @@ -86,7 +86,7 @@ SSD使用一个卷积神经网络实现“端到端”的检测：输入为原 文件共两个字段，第一个字段为图像文件的相对路径，第二个字段为对应标注文件的相对路径。 ### 预训练模型准备 -下载预训练的VGG-16模型，我们提供了一个转换好的模型，下载模型[http://paddlepaddle.bj.bcebos.com/model_zoo/detection/ssd_model/vgg_model.tar.gz](http://paddlepaddle.bj.bcebos.com/model_zoo/detection/ssd_model/vgg_model.tar.gz)，并将其放置路径为```vgg/vgg_model.tar.gz```。 +下载预训练的VGG-16模型，我们提供了一个转换好的模型，下载模型[http://paddlemodels.bj.bcebos.com/v2/vgg_model.tar.gz](http://paddlemodels.bj.bcebos.com/v2/vgg_model.tar.gz)，并将其放置路径为```vgg/vgg_model.tar.gz```。 ### 模型训练 直接执行```python train.py```即可进行训练。需要注意本示例仅支持CUDA GPU环境，无法在CPU上训练，主要因为使用CPU训练速度很慢，实践中一般使用GPU来处理图像任务，这里实现采用硬编码方式使用cuDNN，不提供CPU版本。```train.py```的一些关键执行逻辑： diff --git a/legacy/ssd/README.md b/legacy/ssd/README.md index 22ac492f..7ad8a693 100644 --- a/legacy/ssd/README.md +++ b/legacy/ssd/README.md @@ -77,7 +77,7 @@ The first field is the relative path of the image file, and the second field is ### To Use Pre-trained Model -We also provide a pre-trained model using VGG-16 with good performance. To use the model, download the file http://paddlepaddle.bj.bcebos.com/model_zoo/detection/ssd_model/vgg_model.tar.gz, and place it as ```vgg/vgg_model.tar.gz```。 +We also provide a pre-trained model using VGG-16 with good performance. To use the model, download the file http://paddlemodels.bj.bcebos.com/v2/vgg_model.tar.gz, and place it as ```vgg/vgg_model.tar.gz```. ### Training Next, run ```python train.py``` to train the model. Note that this example only supports the CUDA GPU environment, and can not be trained using only CPU. This is mainly because the training is very slow using CPU only. -- GitLab