Add three trained image classification models on ImageNet. #370
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lcy-seso
requested changes
Oct 13, 2017
image_classification/README.md
Outdated
| @@ -221,3 +221,8 @@ for file_name, result in zip(file_list, lab): | |||
| ``` | |||
|
|
|||
| 首先从文件中加载训练好的模型（代码里以第10轮迭代的结果为例），然后读取`image_list_file`中的图像。`image_list_file`是一个文本文件，每一行为一个图像路径。代码使用`paddle.infer`判断`image_list_file`中每个图像的类别，并进行输出。 | |||
|
|
|||
| ## 使用预训练模型 | |||
| 为方便进行测试和fine-tuning，我们提供了一些对应于示例中模型配置的预训练模型，目前包括ResNet50、ResNet101和Vgg16这几种模型，并提供脚本`model_download.sh`进行模型下载，如下载ResNet50可执行"`sh model_download.sh ResNet50`"，完成后`Paddle_ResNet50.tar.gz`即是相应模型，可参照示例代码进行加载。 | |||
There was a problem hiding this comment.
- 请补充提供一些关于这三个模型的基本训练情况，什么数据集上训练的模型。
- "可参照示例代码进行加载。" -- 什么示例代码，可否说的直接明了一些。
- 目前包括ResNet50、ResNet101和Vgg16这几种模型 --> 目前包括ResNet50、ResNet101和Vgg16。
- 并提供脚本
model_download.sh进行模型下载 --> 请使用脚本model_download.sh进行下载。 - 完成后
Paddle_ResNet50.tar.gz即是相应模型 --> 完成后同目录下的Paddle_ResNet50.tar.gz即是训练好的模型。
image_classification/README.md
Outdated
| ## 使用预训练模型 | ||
| 为方便进行测试和fine-tuning，我们提供了一些对应于示例中模型配置的预训练模型，目前包括ResNet50、ResNet101和Vgg16这几种模型，并提供脚本`model_download.sh`进行模型下载，如下载ResNet50可执行"`sh model_download.sh ResNet50`"，完成后`Paddle_ResNet50.tar.gz`即是相应模型，可参照示例代码进行加载。 | ||
|
|
||
| 需要注意，模型压缩包中所含各文件名对应了模型中的各参数名，这是模型参数加载的依据，所以需要保证网络配置中的参数名能够正确对应到相应的文件。这里提供的模型均使用了示例代码中的配置，如需修改网络配置并使用提供的模型请多加注意。 |
There was a problem hiding this comment.
注意事项：
模型压缩包中所含各文件的文件名和模型配置中的参数名一一对应，是加载模型参数的依据。我们提供的预训练模型均使用了图像分类目录下示例代码中的配置，如需修改网络配置，请多加注意，需要保证网络配置中的参数名和压缩包中的文件名能够正确对应。
lcy-seso
reviewed
Oct 13, 2017
| @@ -0,0 +1,55 @@ | |||
| #! /usr/bin/env bash | |||
There was a problem hiding this comment.
建立一个 models 文件夹，把这个脚本放在 models 下面。
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add three trained image classification models on ImageNet.
fixes #369