edit text

Author: whwnsdlr1

README.md

@@ -1 +1,51 @@
-# tensorflow.js-classification-example
+# tensorflow.js-classification-example
+
+This is a client web application to demonstrate a simple deployment of a classification network using tensorflow.js
+<br />
+currently testing handwriting-number and photograpy possible
+
+## Demo
+you can online demo in [https://whwnsdlr1.github.io/tensorflow.js-classification-example](https://whwnsdlr1.github.io/tensorflow.js-classification-example).
+<br />
+or
+<br />
+install project as below
+```
+git clone https://github.com/whwnsdlr1/tensorflow.js-classification-example
+yarn install
+yarn run serve
+```
+and access to http://localhost:port/tensorflow.js-classification-example
+
+## Usage
+1. draw or upload image
+2. run !
+
+## Browser support - (tested)
+- Google Chrome 77+
+- Mozilla FireFox 68+
+
+## Project setup
+### Customize configuration
+See [Configuration Reference](https://cli.vuejs.org/config/).
+
+## Third-party libraries
+### Dependencies
+- vue: [https://github.com/vuejs/vue](https://github.com/vuejs/vue)
+- tfjs-examples: [https://github.com/tensorflow/tfjs-examples](https://github.com/tensorflow/tfjs-examples)
+- darknet: [https://pjreddie.com/darknet/](https://pjreddie.com/darknet/)
+- d3: [https://github.com/d3/d3](https://github.com/d3/d3)
+- d3-tip: [https://github.com/caged/d3-tip](https://github.com/arian/pngjs)
+- element-resize-event: [https://github.com/KyleAMathews/element-resize-event](https://github.com/KyleAMathews/element-resize-event)
+- vue-lodash: [https://github.com/Ewocker/vue-lodash](https://github.com/Ewocker/vue-lodash)
+- vue-toasted: [https://github.com/shakee93/vue-toasted](https://github.com/shakee93/vue-toasted)
+
+### Dev-Dependencies
+- @vue/cli-plugin-babel
+- @vue/cli-plugin-eslint
+- @vue/cli-service
+- babel-eslint
+- eslint
+- eslint-plugin-vue
+- sitemap-webpack-plugin
+- vue-template-compiler

frontend/README.md

@@ -91,7 +91,7 @@
         <br />
         &nbsp;&nbsp;ML model은 블랙박스로 사용할 수 있지만 세밀한 튜닝을 위해서는 이해가 필요하다.
         특히 classification 문제의 경우 모델이 도대체 무엇을 보고 그런 결정을 판단하는지 확인 할 필요가 있다.
-        이런 "visual explanations"을 producing하는 방법은 occlusion map, Guided-Backpropagation, CAM, Grad-CAM등이 있으며 Grad-CAM의 경우 구조변경과 재학습이 필요 없으며 판단을 내리기 위해 참고한 영역을 표현 할 수 있다.  
+        이런 "visual explanations"을 producing하는 방법은 occlusion map, Guided-Backpropagation, CAM, Grad-CAM등이 있고 Grad-CAM의 경우 구조변경과 재학습이 필요 없으며 판단을 내리기 위해 참고한 영역을 표현 할 수 있다.  
       </p>
     </div>
   </div>