tjbot | IBM TJBot - TJBot was affectionately named after Thomas J | Artificial Intelligence library
kandi X-RAY | tjbot Summary
kandi X-RAY | tjbot Summary
TJBot was affectionately named after Thomas J. Watson, the first Chairman and CEO of IBM. TJBot was created by Maryam Ashoori at IBM Research as an experiment to find the best practices in the design and implementation of cognitive objects. He was born on November 9, 2016 via this blog post.
Support
Quality
Security
License
Reuse
Top functions reviewed by kandi - BETA
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of tjbot
tjbot Key Features
tjbot Examples and Code Snippets
Community Discussions
Trending Discussions on tjbot
QUESTION
I have the following code, straight from the documentation:
...ANSWER
Answered 2018-Dec-06 at 07:34The below code works for me and generating an audio.wav file using the Text-to-Speech API Key
QUESTION
I'm trying to run an electron application on raspberry pi. When I use
var TJBot = require('tjbot') in my code to import a node package, the following error occurs:
ANSWER
Answered 2017-Jul-21 at 18:51Fibers is built to native binary code, it is not pure javascript. Rasperry Pi runs on ARM, which isn't included in the prebuilt binaries. The prebuilt binaries support 32 and 64 bit architectures for OSX (darwin), linux, and windows.
This means you need to manually build Fibers for your system, not install it via NPM. The README for Fibers has clear instructions on how to do so. I've included them here for ease of access. Please follow these instructions to try and get it running on Raspberry Pi / ARM.
Installing from sourcegit clone git://github.com/laverdet/node-fibers.gitcd node-fibersnpm install
Note: node-fibers uses node-gyp for
building. To manually invoke the build process, you can use node-gyp rebuild.
This will put the compiled extension in build/Release/fibers.node. However,
when you do require('fibers'), it will expect the module to be in, for
example, bin/linux-x64-v8-3.11/fibers.node. You can manually put the module
here every time you build, or you can use the included build script. Either
npm install or node build -f will do this for you. If you are going to be
hacking on node-fibers, it may be worthwhile to first do node-gyp configure
and then for subsequent rebuilds you can just do node-gyp build which will
be faster than a full npm install or node-gyp rebuild.
QUESTION
I’m working on a TJBot visual recognition application.
I have some particular questions about retraining.
My case is similar to this:
I have a model trained for cats, dogs and a negative category (not cats or dogs).
The visual recognizer sometimes gets the wrong answer.
What I’d like to do is ‘automatically’ retrain the model, programmatically using an API whenever it gets the wrong answer.
For example after making the wrong determination of a dog when it was actually a cat, I’d like to turn around and call the visual recognition retraining api and indicate: this picture is a cat. This picture is not a dog.
Questions: 1) Is there an API for ‘partial retraining’ using just one image? I don’t want to have to upload hundreds of photos again to completely retrain the model if I don’t have to.
2) In this case I’d like to say this is a positive example of a cat, and a negative example of a dog. As I understand it there’s no way to indicate ‘negative example of a dog’. I can only say ‘negative example of cat and dog’. Is there a way to indicate ‘negative example of just one of the trained classes?
3) If there’s no API, can I accomplish #1 or #2 using the ‘studio’ website? How?
Thanks, Andy Citron (IBM retired)
...ANSWER
Answered 2018-Sep-11 at 02:46Thanks for your question.
Yes, you can send a single image as the data for retraining a classifier. However, 1 image is unlikely to affect your classifier much. We suggest sending at least 10 new images in each retraining request.
If sent as a "negative_example" the image should be neither a cat or a dog. The classes in a classifier should be mutually exclusive. A photo of a cat and dog together does not work well for training a system which is trying to tell the difference between the two types. To the classifier, the types of answers it can give are defined by the classes, or if negative_examples are used "none of the above". So in your example, every image in the world gets classified by this model as either cat, dog, or neither.
The API is documented here: https://www.ibm.com/watson/developercloud/visual-recognition/api/v3/curl.html?curl#update-classifier
QUESTION
Found in service examples, a working conversation script. Thanks again to @Taj!
I feel like I am very very close to get it to work. I have done the samething on Raspberry Pi with TJBot, so I have all the accounts, and I linked all the credentials correctly including the workplace ID from Conversation tooling. I am using Unity 3D 5.5.1f1 and the latest SDK, the one that was updated 13 days ago.
I copied and pasted the sample code for conversation on SDK's github page into a brand new C# file:
...ANSWER
Answered 2017-Feb-09 at 17:00The response strings are an array in the resp object.
Community Discussions, Code Snippets contain sources that include Stack Exchange Network
Vulnerabilities
No vulnerabilities reported
Install tjbot
3d Print or Laser Cut. If you have access to a 3D printer or laser cutter, you can print/cut TJBot yourself. Begin by downloading the design files and firing up your printer/cutter.
TJBot Full Kit. You can order a full TJBot kit with the laser cut cardboard and all the electronics from Sparkfun, Adafruit, or Robotkingdom.
TJBot Cardboard Kit. You can purchase the TJBot laser cut cardboard from Texas Laser Creations.
Support
Reuse Trending Solutions
Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items
Find more librariesStay Updated
Subscribe to our newsletter for trending solutions and developer bootcamps
Share this Page
