ZIP2323232323323232 62.82MB

qq_40898875需要积分:4(1积分=1元)

资源文件列表:

gradient_descent_viz-master.zip 大约有42个文件
  1. gradient_descent_viz-master/
  2. gradient_descent_viz-master/.gitignore 737B
  3. gradient_descent_viz-master/LICENSE 1.04KB
  4. gradient_descent_viz-master/README.md 4.51KB
  5. gradient_descent_viz-master/gradient_descent_visualization-macOS64bit.dmg 11.92MB
  6. gradient_descent_viz-master/gradient_descent_visualization.pro 457B
  7. gradient_descent_viz-master/gradient_descent_viz_windows64bit.zip 23.84MB
  8. gradient_descent_viz-master/headers/
  9. gradient_descent_viz-master/headers/animation.h 7.33KB
  10. gradient_descent_viz-master/headers/gradient_descent.h 3.37KB
  11. gradient_descent_viz-master/headers/item.h 3.67KB
  12. gradient_descent_viz-master/headers/plot_area.h 2.16KB
  13. gradient_descent_viz-master/headers/point.h 189B
  14. gradient_descent_viz-master/headers/window.h 1.41KB
  15. gradient_descent_viz-master/resources/
  16. gradient_descent_viz-master/resources/icons/
  17. gradient_descent_viz-master/resources/icons/zoomin.png 24.69KB
  18. gradient_descent_viz-master/resources/icons/zoomout.png 23.49KB
  19. gradient_descent_viz-master/resources/mesh/
  20. gradient_descent_viz-master/resources/mesh/largesphere.obj 59.86KB
  21. gradient_descent_viz-master/resources/mesh/narrowarrow copy.obj 11.51KB
  22. gradient_descent_viz-master/resources/mesh/narrowarrow.obj 10.51KB
  23. gradient_descent_viz-master/resources/mesh/plane copy1.obj 994B
  24. gradient_descent_viz-master/resources/mesh/plane elongated.obj 985B
  25. gradient_descent_viz-master/resources/mesh/plane.obj 929B
  26. gradient_descent_viz-master/resources/resources.qrc 263B
  27. gradient_descent_viz-master/resources/screenshots/
  28. gradient_descent_viz-master/resources/screenshots/code_structure_diagram.png 9.69KB
  29. gradient_descent_viz-master/resources/screenshots/code_structure_visual.png 131.58KB
  30. gradient_descent_viz-master/resources/screenshots/demo-overview.gif 10.21MB
  31. gradient_descent_viz-master/resources/screenshots/demo-parameter-tuning.gif 6.85MB
  32. gradient_descent_viz-master/resources/screenshots/demo-path.gif 1.69MB
  33. gradient_descent_viz-master/resources/screenshots/demo-step-by-step.gif 237.11KB
  34. gradient_descent_viz-master/resources/screenshots/demo-surface.gif 8.18MB
  35. gradient_descent_viz-master/resources/screenshots/demo-visual-elements.gif 933KB
  36. gradient_descent_viz-master/src/
  37. gradient_descent_viz-master/src/animation.cpp 30.27KB
  38. gradient_descent_viz-master/src/gradient_descent.cpp 7.37KB
  39. gradient_descent_viz-master/src/item.cpp 9.41KB
  40. gradient_descent_viz-master/src/main.cpp 178B
  41. gradient_descent_viz-master/src/plot_area.cpp 9.73KB
  42. gradient_descent_viz-master/src/window.cpp 15.14KB

资源介绍:

323232211111111111111111113esdsfsdf
# Gradient Descent Visualization Gradient Descent Viz is a desktop app that visualizes some popular [gradient descent methods](https://en.wikipedia.org/wiki/Stochastic_gradient_descent) in machine learning, including (vanilla) gradient descent, momentum, AdaGrad, RMSProp and Adam. My hope is that by playing around with the different settings, anyone -- beginner or expert -- can come away with new intuitive understanding of these methods. Read here for the [accompanying blog post](https://towardsdatascience.com/a-visual-explanation-of-gradient-descent-methods-momentum-adagrad-rmsprop-adam-f898b102325c) that explains these methods in detail. ![demo](resources/screenshots/demo-overview.gif) ## Features * Choose between a few different surfaces. For example, in the screen recording below, you can see that Adam and RMSProp handle saddle points much better than simple gradient descent or momentum. ![demo](resources/screenshots/demo-surface.gif) * Tune parameters. The demo shows a surface with a plateau (right click and drag to rotate, arrow keys to navigate, and ctrl (or cmd) + plus / minus to zoom). Momentum method with a low learning rate is not enough to propel it through the flat region. Dialing up the learning rate solves the issue. Play around with the other parameters too and see what you find. ![demo](resources/screenshots/demo-parameter-tuning.gif) * Watch step-by-step cartoon to visualize the calculation process of each method. Below is a demo of inner workings of momentum descent. ![demo](resources/screenshots/demo-step-by-step.gif) * Use visual elements to track things such as the gradient, the momentum, sum of squared gradient (visualized by squares whose sizes correspond to the magnitude of the term), adjusted gradient (after dividing by the sum of squared gradient or adding on momentum, depending on the method), and the path. In the example below, you can see that after adjusted by the sum of squared gradient, RMSProp takes a very different direction. Comparing that with AdaGrad, one will visually see that the sum of squared gradient for AdaGrad is much bigger in scale (because it doesn't decay). You can use this feature to understand what makes each method work or not work under different circumstances. ![demo](resources/screenshots/demo-visual-elements.gif) * Draw path of the descents. See how different methods reach the destination in different manners. ![demo](resources/screenshots/demo-path.gif) ## Building This is a C++ app written in Qt, using the free Qt open-source licensed version. It works cross platform. For pre-built app for MacOS (64 bits), download the file [gradient_descent_visualization-macOS64bit.dmg](gradient_descent_visualization-macOS64bit.dmg) from this repository. Extract the image and run the app (you may need to right click -> open to grant permission to open an app from an unknown developer). For pre-built app for Windows (64 bits), download the file [gradient_descent_viz_windows64bit.zip](gradient_descent_viz_windows64bit.zip) from this repository. Decompress the zip and run the .exe file. To build it from source code, download and install Qt 5.10 or above (https://www.qt.io/download) for your platform. This app uses the Qt Data Visualization package; make sure to include that in your installation as well. Checkout this repository, and build and run gradient_descent_visualization.pro within the Qt Creator IDE. ## Code Structure * The window class is responsible for the UI layout, including all the widgets (spinbox, input text box, etc) on the side bar. * The plot_area class is responsible for actions happen inside the plot region, including methods that respond to user inputs using the widgets (e.g. play / pause, change playback speed, change surface, etc). * The animation class controls the logic for animation. Each descent method has its own derived animation class, which owns the animated ball, arrows, etc. The class controls the creation and destruction of these objects as well as their placement and properties (such as magnitude and color). * The item class and its derived classes inherit QtCustom3DItem and are implementations of our customed items such as the arrows, the squares, the path (which is really just a 3D surface), etc. * The GradientDescent class and its derived classes are the mathematic implementations of each descent method. ![code structure](resources/screenshots/code_structure_diagram.png) ![code strucutre](resources/screenshots/code_structure_visual.png) ## Contribution Contributions are welcome. Looking for help to turn this project into a webapp.
100+评论
captcha
    相关资源
    类型标题大小时间
    ZIP龙讯lt6911uxc,lt9611uxc资料，有源码固件，支持4k60，支持对接海思3519a和3559a，hdmi转mipi，双通道4k6097.74KB4月前
    ZIP一种基于扩展反电动势的永磁同步电机无位置控制算法，全部C语言 编写，含有矢量控制大部分功能(弱磁，解耦，过调制，死区补偿等)为了方便学习和工作，该产品结合S-Function进行仿真，且属于量产产品635.82KB4月前
    ZIP龙讯lt6911uxc,lt9611uxc资料，有源码固件，支持4k60，支持对接海思3519a和3559a，hdmi转mipi，双通道4k6099.96KB4月前
    ZIP数据结构 (1)(1).zip7.09MB4月前
    ZIPComsol模拟飞秒激光烧蚀双温方程热力耦合模型225.27KB4月前
    ZIPCOMSOL石墨烯 钙钛矿太阳能电池仿真模型 光电耦合模型，文章复现 125.12KB4月前
    ZIPOnvif服务端开发源码46.13MB4月前
    ZIP谷歌呃呃呃呃呃呃呃呃呃呃呃呃2.5MB4月前