diff --git a/docs/todo_list.md b/docs/todo_list.md index 547217b..86b6b12 100644 --- a/docs/todo_list.md +++ b/docs/todo_list.md @@ -22,18 +22,16 @@ - add node (add preprocess nodes): https://zhuanlan.zhihu.com/p/394395167 -combine models (not supported): +- combine models (not supported): - - https://stackoverflow.com/questions/66178085/can-i-combine-two-onnx-graphs-together-passing-the-output-from-one-as-input-to + - https://stackoverflow.com/questions/66178085/can-i-combine-two-onnx-graphs-together-passing-the-output-from-one-as-input-to - - https://www.zhihu.com/people/kai-xin-zui-zhong-yao-76/posts + - https://www.zhihu.com/people/kai-xin-zui-zhong-yao-76/posts - modify attribute of nodes (supported) - topk: https://github.com/onnx/onnx/issues/2921 - - remove layer (supported): https://github.com/onnx/onnx/issues/2638 - diff --git a/docs/update_log.md b/docs/update_log.md index 86f6fb6..f6134d9 100644 --- a/docs/update_log.md +++ b/docs/update_log.md @@ -1,6 +1,11 @@ # onnx-modifier update log +## 20220620 + +add Windows executable file. + ## 20220612 + - update graph automatically as soon as a modification is invoked. - fix `shared arguments` issue. - support editing the attributes and the name of inputs/outputs directly in the placeholders in the sidebar. diff --git a/readme.md b/readme.md index 2991db5..2a1fc3e 100644 --- a/readme.md +++ b/readme.md @@ -2,8 +2,6 @@ English | [简体中文](readme_zh-CN.md) -> In this branch - # Introduction To edit an ONNX model, One common way is to visualize the model graph, and edit it using ONNX Python API. This works fine. However, we have to code to edit, then visualize to check. The two processes may iterate for many times, which is time-consuming. 👋 @@ -24,6 +22,7 @@ Currently, the following editing operations are supported: - [x] Edit the attribute of nodes - [x] Add new nodes (experimental) +Here is the [update log](./docs/update_log.md) and [TODO list](./docs/todo_list.md). Hope it helps! @@ -51,8 +50,8 @@ python app.py Click the url in the output info generated by flask (`http://127.0.0.1:5000/` for example), then `onnx-modifier` will be launched in the web browser. ## launch from executable file -- Windows: Download [onnx-modifier.exe](https://drive.google.com/file/d/1y7mYlvF0G5iiNDgOFh1ESXlTs8I2ipVQ/view?usp=sharing), double-click it and enjoy. - - Egde browser is used for viewing by default. +- Windows: Download [onnx-modifier.exe (27.6MB)](https://drive.google.com/file/d/1y7mYlvF0G5iiNDgOFh1ESXlTs8I2ipVQ/view?usp=sharing), double-click it and enjoy. + - Edge browser is used for runtime environment by default. > I recorded how I made the the executable file in `app_desktop.py`. The executable file for other platforms are left for future work. @@ -153,13 +152,6 @@ For quick testing, some typical sample models are provided as following. Most of `onnx-modifier` is under active development 🛠. Welcome to use, create issues and pull requests! 🥰 -# TODO - -- [ ] Create executable file for easier launching for the following platforms: - - [ ] Linux - - [x] Windows -- [ ] Add `merge models` feature - # Credits and referred materials - [Netron](https://github.com/lutzroeder/netron) diff --git a/readme_zh-CN.md b/readme_zh-CN.md index b571484..e383ccb 100644 --- a/readme_zh-CN.md +++ b/readme_zh-CN.md @@ -26,6 +26,9 @@ `onnx-modifier`基于流行的模型可视化工具 [Netron](https://github.com/lutzroeder/netron) 和轻量级Web应用框架 [flask](https://github.com/pallets/flask) 开发。希望它能给社区带来一些贡献~ # 安装与运行 +目前支持两种方法运行`onnx-modifier`： + +## 源码+命令行启动 - 拉取`onnx-modifier`，安装所需要的Python库 @@ -43,7 +46,12 @@ python app.py ``` - 点击输出中的url（如`http://127.0.0.1:5000/`），即可在浏览器中进入onnx-modifier界面。点击`Open Model...`，上传所需要编辑的模型文件，上传完毕后，网络可视化结构会自动显示。 +## 从可执行文件启动 +- Windows: 下载可执行文件[onnx-modifier.exe (27.6MB)](https://drive.google.com/file/d/1y7mYlvF0G5iiNDgOFh1ESXlTs8I2ipVQ/view?usp=sharing)，双击即可启动。 + - 默认使用Edge浏览器作为运行环境。 +> 生成可执行文件的步骤记录在`app_desktop.py`文件中。未来会为其他平台生成可执行文件。 + +点击输出中的url（如`http://127.0.0.1:5000/`），即可在浏览器中进入onnx-modifier界面。点击`Open Model...`，上传所需要编辑的模型文件，上传完毕后，网络可视化结构会自动显示。 # 用法