• [paper] [semi supervised semantic segmentation]advantageous learning for semi supervised semantic segmentation


    Adversarial Learning for Semi-Supervised Semantic Segmentation Original paper abstract Innovation: we propose a semi supervised semantic segmentation method using confrontation network.In the traditional Gan network, the discriminator is mostly used to classify the authenticity of the input image (the image of the sample in datasets is scored high, and the image generated by the generator […]

  • Glsl shader, come and play


    For the front-end students who realize animation,canvasIt can be said to be the most free and comprehensive animation implementation carrier. Not only can it passjavascriptControl the drawing of points, lines and faces, and fill them with picture resources; It can also change the input parameters to make interactive animation, and fully control the action trajectory, […]

  • Mosaic pictures


    The code comes from the headline “front-end Xiaozhi“, which is deleted by infringement <!DOCTYPE html> <html lang=”en”> <head> <meta charset=”UTF-8″> <meta http-equiv=”X-UA-Compatible” content=”IE=edge”> <meta name=”viewport” content=”width=device-width, initial-scale=1.0″> <title> suspended mosaic </title> <style> * { margin: 0; padding: 0; box-sizing: border-box; } body { width: 100%; height: 100vh; background: #000; display: flex; justify-content: center; align-items: center; […]

  • Analysis of MNIST data set with R language: exploring handwritten numeral classification


    Original link:http://tecdat.cn/?p=5246 Source of original text:Tuoduan data tribe official account Definition of the difference between data science and machine learning: data science focuses on extracting insight, while machine learning is interested in prediction. I also note that these two areas are quite different: I use both machine learning and data science in my work: I […]

  • HTML table markup tutorial (31): width and height attributes of cells width and height


    By default, the width and height of cells are automatically adjusted according to the content. We can also manually set the width and height of cells.Basic grammar <TD WIDTH=value HEIGHT=value> Grammatical interpretation The width attribute defines the width of the cell, and the height attribute defines the height of the cell, in pixels or percentages.Example […]

  • OpenGL realizes the function of drawing revision (P drawing)


    Android OpenGL implements p-graph function P-graph function and OpenGL P-graph function and OpenGL Friends who have played with P-map software must know something about this function. We can simply see P-map as moving the pixels in an area in a certain direction to produce a certain deformation effect. Based on this principle, we can manually […]

  • Go deep into the pits that the mobile terminal adapts to: decimal pixels, blurred images


    1、 Advantages and disadvantages of adaptation scheme zoom At first, it was written directly in PX, and then the scale in the meta tag was used to scale the entire page. It was simple and crude. The advantage is simple and fast. The disadvantage is that you can’t control the scaling of some styles, and […]

  • Map custom tags used by Tencent map JavaScript API


    Tencent location service JavaScript API is a map application programming interface developed by JavaScript language. On this basis, Tencent location service has launched its upgraded version of JavaScript API GL, which is a set of 3D version map API encapsulated based on the high-performance 3D rendering engine implemented by webgl. The 3D vision is more […]

  • 5、 OpenGL texture


    Audio and video development: summary of OpenGL + OpenGL es + metal series articles Texture can package objects to display different patterns. This paper begins to understand the texture and master how to set the texture Main contents:1. Texture recognition2. Texture settings3. Texture coordinates4. Pyramid case 1. Texture recognition Texture is a kind of graphic […]

  • Implement SLIC algorithm to generate pixel pictures


    preface Pixel style first appeared in 8bit video games. Restricted by the size of computer memory and single display color, it can only use a small number of pixels to present content, but it has achieved many classic pixel games. With the improvement of memory capacity and screen resolution, the limitation of memory and display […]

  • Training lenet to recognize handwritten digits based on mindspore


    Reprint address:https://bbs.huaweicloud.com/f… Author: Huha Huha Note that the test code loads the network through import and getattr. If the name of the training script is modified, the corresponding modulepath name also needs to be modified # load the network definition module = importlib.import_module(modulePath) network = getattr(module, moduleName)() Otherwise, the network cannot be loaded, and the […]

  • The enigmatic “steganography” is not exclusive to hacker agents – I use the front-end steganography, which is very interesting ❗


    preface Hello, everyone ~ I’m Rongding, Mid Autumn Festival is coming soon ~ first of all, I wish you a Happy Mid Autumn Festival, family reunion, happiness and well-being~ The reason for this issue of copyright protection content is that some time ago, a group of friends said that his article had been stolen, so […]