azure-cognitive-services

Retrieving Chat Bot conversation data in Azure

纵饮孤独 提交于 2019-12-06 08:52:51
问题 A brief background first: The Bot framework stores the conversation data within a storage either Azure tables/Cosmos DB (Azure tables in my case). For each conversation there is an entry made into the Azure table with the timestamp, userid, conversation messages and other details. I am trying to retrieve the conversation details from Azure table storage using custom code in C# as shown below. Microsoft.WindowsAzure.Storage.CloudStorageAccount storageAccount = Microsoft.WindowsAzure.Storage

How to integrate LUIS and QnA Maker services in single Node.js bot?

a 夏天 提交于 2019-12-05 10:08:59
I'm developing a chatbot using Microsoft Bot Framework with Node.js SDK. I've integrated LUIS and QnA maker but I want to create this scenario if it's possible. Taking in example the following link and in particular this section: There are a few ways that a bot may implement a hybrid of LUIS and QnA Maker: Call LUIS first, and if no intent meets a specific threshold score, i.e., "None" intent is triggered, then call QnA Maker. Alternatively, create a LUIS intent for QnA Maker, feeding your LUIS model with example QnA questions that map to "QnAIntent." Just an example: I have my QnA KB in which

Use Azure custom-vision trained model with tensorflow.js

偶尔善良 提交于 2019-12-05 02:41:01
问题 I've trained a model with Azure Custom Vision and downloaded the TensorFlow files for Android (see: https://docs.microsoft.com/en-au/azure/cognitive-services/custom-vision-service/export-your-model). How can I use this with tensorflow.js? I need a model (pb file) and weights (json file). However Azure gives me a .pb and a textfile with tags. From my research I also understand that there are also different pb files, but I can't find which type Azure Custom Vision exports. I found the tfjs

Azure Cognitive Services OCR giving differing results - how to remedy?

霸气de小男生 提交于 2019-12-05 00:47:25
问题 Azure CS has an OCR demo (westcentralus endpoint) at https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/?v=18.05 On a poor test image (which I'm afraid I can't post because it's an identity document), I get OCR results that 100% match the actual text for three test cases in fact - remarkable. However, when I follow the sample at the URL below, with the westeurope endpoint, I get poorer OCR results - some text is missing: https://docs.microsoft.com/en-us/azure

Use Azure custom-vision trained model with tensorflow.js

一个人想着一个人 提交于 2019-12-03 17:07:27
I've trained a model with Azure Custom Vision and downloaded the TensorFlow files for Android (see: https://docs.microsoft.com/en-au/azure/cognitive-services/custom-vision-service/export-your-model ). How can I use this with tensorflow.js ? I need a model (pb file) and weights (json file). However Azure gives me a .pb and a textfile with tags. From my research I also understand that there are also different pb files, but I can't find which type Azure Custom Vision exports. I found the tfjs converter . This is to convert a TensorFlow SavedModel (is the *.pb file from Azure a SavedModel?) or

Getting `Status Code:400 Bad Request` When calling Microsoft Azure Emotion API with data of type `Content-Type:application/octet-stream`

老子叫甜甜 提交于 2019-12-02 14:56:35
问题 I'm trying to send data to Microsoft Cognitive Services' Emotion API, in the form of Content-Type: application/octet-stream . I'm getting the Base64 string of an image from a canvas by calling canvas.toDataURL('image/jpeg', 0.1); (I've tried calling it with 1, 0.5, 0.2 as well, just to check whether it works and stops giving me errors) Then with that Base64 string, I'm calling the EmotionService's getUserEmotion method. I followed the instructions mentioned in this answer, to make an AJAX

Getting `Status Code:400 Bad Request` When calling Microsoft Azure Emotion API with data of type `Content-Type:application/octet-stream`

微笑、不失礼 提交于 2019-12-02 10:25:11
I'm trying to send data to Microsoft Cognitive Services' Emotion API , in the form of Content-Type: application/octet-stream . I'm getting the Base64 string of an image from a canvas by calling canvas.toDataURL('image/jpeg', 0.1); (I've tried calling it with 1, 0.5, 0.2 as well, just to check whether it works and stops giving me errors) Then with that Base64 string, I'm calling the EmotionService's getUserEmotion method. I followed the instructions mentioned in this answer , to make an AJAX call using Angular's HttpClient. Here's what my service looks like: import { Injectable } from '@angular