Image-to-Image Demo - Affine Layer Interactive Image Translation with pix2pix-tensorflow The pix2pix model works by training on pairs of images such as building facade labels to building facades, and then attempts to generate the corresponding output image from any input image you give it. The idea is straight from the pix2pix paper, which is a good read. edges2cats Trained on about 2k stock cat photos and edges automatically generated from those photos. Some of the pictures look especially creepy, I think because it's easier to notice when an animal looks wrong, especially around the eyes. facades Trained on a database of building facades to labeled building facades. I didn't have the names of the different parts of building facades so I just guessed what they were called. edges2shoes Trained on a database of ~50k shoe pictures collected from Zappos along with edges generated from those pictures automatically. edges2handbags Implementation The pre-trained models are available in the Datasets section on GitHub.
Creating Chat Bot using 100% ASP.NET Core 2.0 Web API and Microsoft Bot Framework - Riza Marahaban Bot Application with BotBuilder SDK To create a chat bot application using .NET Framework, you might already know this type of Bot Application template when launching new project in Visual Studio 2017. The problem is, the NuGet packages and the template project which is from the BotBuilder SDK currently only support .NET Framework 4.6 and above as stated on the page and not yet supporting .NET Core related. Here is the message from the docs page: Well, since the Bot Builder SDK is an Open-Source stuff, we can visit the source code from GitHub itself and see what Microsoft and the communities is up to to with regards to supporting .NET Core 2.0 related. We are in luck. Here is what you might see in the terminal: Once you settle the cloning, we can create the ASP.NET Core 2.0 Web API. Remember: Bot API is just a Web API Yes, it is just a normal Web API that you can create using ASP.NET Core 2 Web API template project. Then, choose Web API with ASP.NET Core 2.0 option. Add the Code Source Code
Keras Documentation Register A Chat Bot Using MS Bot Framework Recently, I created a chatbot. After an implementation of Bot using MS Bot framework, it should be registered with These are a few steps which may help you to register and get ready to use it. Step 1 Go to You will have the following section there as given in the below screenshot. Step 2 Click on "My Bots" and further, click on "Create a bot". Step 3 Click on "Create" button as shown in given image and the following window will appear. Step 4 Choose the first option from the given screen and click OK. Step 5 As soon as you create click ok, it generates AppId which might be essential at down the level during accessing the Bot which you have created. Step 6 Click on "Generate an app password" to continue. Note Kindly save this password in Notepad for future purposes. Step 7 After performing all the above steps, it is time to set configuration as given below. It may prompt you to keep https instead of http, Step 8 Step 9 Step 10
TF Jam — Shooting Hoops with Machine Learning – TensorFlow By Abe Haskins (Twitter, Github) In this article, we’ll dive into using Unity3D and TensorFlow to teach an AI to perform a simple in-game task: shooting balls into a hoop. The complete source code is available on Github, if you have any questions reach out to me on Twitter. An Introduction to our Game There is a game where players have one main goal: get a ball into a basket. If you’ve ever played NBA Jam or any of the games it inspired (including the real life NBA league, which I think came after NBA Jam) then you know the mechanic to shoot a ball, from the player’s perspective, is fairly simple. If you were a smart, math-inclined person you may be able to figure out these answers with pen and paper, however the author of this blog post failed 8th grade algebra, so… those “smart person” answers are out of the question. Getting Started We’ll need a handful of things to walk through this project. If you’re not an expert in any of these technologies, that is totally okay! Download the Project
Saving State data with BotBuilder-Azure in Node.js - Microsoft Bot Framework We’ve discussed strategies to store state data for bots in .NET, in this article we’ll demonstrate how to do the same for bots built using the Bot Builder SDK for Node.js. In this sample, we’ll be leveraging the botbuilder-azure npm module to save our conversation state data to Azure DocumentDB. Initial Setup Ensure you have Node.js installed.You’ll need an Azure Account. Note: DocumentDB was recently rebranded to Azure Cosmos DB, click here for details Use an existing Node.js bot, or create a new one. Bot setup to use Azure DocumentDB The full sample on Github can be found here. Install the botbuilder-azure node module using npm per the following command: Require the newly installed module in the bot application. // app.js ... var azure = require('botbuilder-azure'); ... Next we’ll configure the connection settings to connect to the Azure: Note: If the database and collection does not exist in the Azure database, they will be automatically created for you. Why use a Custom State Client Summary
Picking a Chatbot Framework: Botkit vs Microsoft Bot Builder In the world of custom built bots there are two frameworks which reign supreme. Microsoft Bot Framework and Botkit. Both have SDKs that help developers build bots. As a contributor to Botkit, I see people ask in issues what the difference between Botkit and Microsoft Bot Framework are, and why they should choose one over the other. Here’s a quick answer for anyone who is building a bot and wondering which framework they should choose! Every bot developer faces the same challenges: receive messages from a Platform, understand the user’s intent, respond accordingly. Personally, I build bots with Botkit because it allows me to control all aspects of the interaction, and supports an open ended number of platforms. Botkit and Microsoft Bot Framework are both open source bot frameworks that do all that for you, so you can focus on building an interaction. Microsoft Bot Builder Quick Clarification, per docs: MS Bot Builder is the sdk you use to create bots which connect to MS Bot Framework. Botkit
Microsoft/BotFramework-WebChat: Embeddable web chat control for the Microsoft Bot Framework New Look of LUIS (Language Understanding Intelligent Service) Introduction Among the many Cognitive services introduced by Microsoft LUIS (Language Understanding Intelligent Service) is one which plays an important role in adding the natural language understanding capability to your apps. LUIS allows your application to attain the capability of understanding whatever the user wants or asks for in their own words or language. LUIS is the key part of the bot brain that allows the bot to understand natural language input and reason about it to take the appropriate action. It is always important to plan your LUIS app before you actually create a one. Once you start building the LUIS model with a use case, then the initial step you need to do is to list down the general user intensions like “bookflight” or “cancelappointment”, etc. Background Hope you have a pretty good knowledge on Microsoft Azure and LUIS as you are reading this article. LUIS Key Concepts Some of the key concepts you need to be aware of prior to creating a new LUIS app are: New Features
How to work with Microsoft bot framework since last update If you work with Microsoft bot framework you probably have seen the banner inviting to migrate your bot. You can check the web for creating bots is not exactly the same, there are some things that are gone. The settings and testing area of the bots you had created before the update are still enabled and visible from dev.botframework.com. Nevertheless, if you create a new bot the settings area have changed.Perhaps in the old bots settings, if they are not migrated yet, the web view looks odd, will tell you here why. 1. The way of creating bots has changed a bit. Once inside Azure, you will see 3 kinds of ways to create a bot:- Web app bot- Bot channel registration- Functions bot In this post, we are going to see some theory and practice of how to work with the new version of the bot. 2. a. This is the classic implementation of a web chatbot. Once the bot is created it will need to have one name for the bot and another for the web app. b. The only way of hosting your bot is Azure. c. d. e.
Managing state and logging chat history in Microsoft bot framework In our earlier posts on Microsoft bot framework we have see basic formflow feature of bot framework and some of the advanced stuffs as well. In this blog we are going to discuss about what all are the ways in which we can manage conversation states in bot framework and how we can maintain conversation history, i.e how we can maintain a log of all the conversations that are taking place between the bot and its users. Before we proceed on how to do that lets talk about scenarios why they are necessary and what all are the use case that it can serve. Lets proceed one by one and start with state management first. Manage state data: The Bot Framework State service enables your bot to store and retrieve state data that is associated with a user, a conversation, or a specific user within the context of a specific conversation. If your bot uses dialogs, conversation state (the dialog stack and the state of each dialog in the stack) is automatically stored using the Bot Framework State service. 4.
Introducing Windows Azure Hosted Node.js By John V. Petersen In a previous article, I wrote about how simple it is to deploy an ASP.NET MVC Web Application to Windows Azure using Team Foundation Service hosted at tfspreview.com. In this article, I will build on those concepts and show you how to build and deploy a simple Node.js website to Azure using Git as the source code repository. Setting Up Your Machine It’s quite likely you won’t have the necessary software installed to work through this article’s example. Node.js (nodejs.org)Git (git-scm.com) You will also need the Node.js Azure SDK, which you can download from Installing and Running Node.js Node.js is a server-side JavaScript hosting environment. Even if you are not fluent with JavaScript, the simple Hello World example is very simple to follow. To further illustrate the Node.js API, consider Listing 1, which interrogates the URL for a specific query string: "C:\Program Files\nodejs\node.exe" server.js Installing Git