From 3f9c2f8bac68ce97ed6575824a2859a425bf5cb0 Mon Sep 17 00:00:00 2001
From: wangqun <wangqun@baidu.com>
Date: Wed, 18 Mar 2020 19:25:57 +0800
Subject: [PATCH] [doc] op list

[doc] op list
---
 web/src/factory/fshader/README.md    | 42 ++++++++++++++++++++++++++++
 web/src/factory/fshader/README_cn.md | 40 ++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)
 create mode 100644 web/src/factory/fshader/README.md
 create mode 100644 web/src/factory/fshader/README_cn.md

diff --git a/web/src/factory/fshader/README.md b/web/src/factory/fshader/README.md
new file mode 100644
index 0000000000..7d38c5c569
--- /dev/null
+++ b/web/src/factory/fshader/README.md
@@ -0,0 +1,42 @@
+[中文版](./README_cn.md)
+# PaddleJS Operators Support Table
+
+Operators represent the operators corresponding to each layer of the neural network. Refer to the specific algorithm implementation, the table shows the support of Baidu artificial intelligence operators. Padderjs currently supports GPU operation calculation version.
+
+See Compatibility for a list of the supported platforms.
+
+Please refer to compatibility for the list supported by paddle.js. This file will change as the number of operators increases and the support situation changes.
+
+Baidu paddlejs uses the ready-made JavaScript model or transforms the paddle model to run in the browser.
+
+## Demonstration
+
+
+| Operator      | Gpu Backend    | desc     |
+| ------------- | ------------- | ------------- |
+| conv2d_transpose   |  webGL1、 webGL2   | |
+| conv2d   |  webGL1、 webGL2   | |
+| conv2d_depthwise   |  webGL1、 webGL2   | |
+| conv2d_elementwise_add   |  webGL1、 webGL2   | |
+| conv2d_elementwise_add_winograd   |  webGL1、 webGL2   | |
+| dynamic   |  webGL1、 webGL2   | |
+| scale   |  webGL1、 webGL2   | |
+| pool2d   |  webGL1、 webGL2   | |
+| pool2d_max   |  webGL1、 webGL2   | |
+| pool2d_winograd   |  webGL1、 webGL2   | |
+| elementwise_add   |  webGL1、 webGL2   | |
+| mul   |  webGL1、 webGL2   | |
+| relu   |  webGL1、 webGL2   | |
+| relu6   |  webGL1、 webGL2   | |
+| softmax   |  webGL1、 webGL2   | |
+| batchnorm   |  webGL1、 webGL2   | |
+| reshape   |  webGL1、 webGL2   | |
+| transpose   |  webGL1、 webGL2   | |
+
+
+## Browser coverage
+
+* PC: Chrome
+* Mac: Chrome
+* Android: Baidu App and QQ Browser
+
diff --git a/web/src/factory/fshader/README_cn.md b/web/src/factory/fshader/README_cn.md
new file mode 100644
index 0000000000..9ec3d75d29
--- /dev/null
+++ b/web/src/factory/fshader/README_cn.md
@@ -0,0 +1,40 @@
+# PaddleJS Operators 支持表
+
+Operators表示神经网络每层对应的算子，参考具体的算法实现，表格显示了百度人工智能算子支持情况，PadderJS目前支持GPU操作计算版本。
+
+受paddle.js支持的列表，请参阅兼容性，此文件会随着Operator数量增加和支持情况做相应的变更。
+
+
+
+## 演示
+
+| Operator      | Gpu Backend    | desc     |
+| ------------- | ------------- | ------------- |
+| conv2d_transpose   |  webGL1、 webGL2   | |
+| conv2d   |  webGL1、 webGL2   | |
+| conv2d_depthwise   |  webGL1、 webGL2   | |
+| conv2d_elementwise_add   |  webGL1、 webGL2   | |
+| conv2d_elementwise_add_winograd   |  webGL1、 webGL2   | |
+| dynamic   |  webGL1、 webGL2   | |
+| scale   |  webGL1、 webGL2   | |
+| pool2d   |  webGL1、 webGL2   | |
+| pool2d_max   |  webGL1、 webGL2   | |
+| pool2d_winograd   |  webGL1、 webGL2   | |
+| elementwise_add   |  webGL1、 webGL2   | |
+| mul   |  webGL1、 webGL2   | |
+| relu   |  webGL1、 webGL2   | |
+| relu6   |  webGL1、 webGL2   | |
+| softmax   |  webGL1、 webGL2   | |
+| batchnorm   |  webGL1、 webGL2   | |
+| reshape   |  webGL1、 webGL2   | |
+| transpose   |  webGL1、 webGL2   | |
+
+
+
+## 浏览器覆盖面
+
+* PC: Chrome
+* Mac: Chrome
+* Android: Baidu App and QQ Browser
+
+
-- 
GitLab