Comments (1)
I agree that this is clearly a bug. Nevertheless, I wanted to report another issue related to this one. If you click the Discetize output, it does have to update the training loss numerical value and graph, but just once. Whenever you discretize the space and neglect the existence of the"gradient" colours, you only have 2 static values for the predicted values, hence calculating the loss would result in a different result.
from playground.
Related Issues (20)
- Magic number
- Why aren't you saying in the Title Area a statement something like this TensorFlow model is using CNN, RNN or whatever form of NNN your using. HOT 1
- visualization_Locally
- upload my own data
- Feature request: Cross-entropy error function
- i farded HOT 1
- Unable to see dataset options
- How feature visualisation works? HOT 1
- about the code update weight in the function updateWeights.
- Make it easier to understand with cats & dogs database
- our own data HOT 1
- Yes, here are two examples I am aware of:
- Invitation to Collaborate: Enhancing TensorFlow Playground for Beginners and Beyond.
- Final output values do not make mathematical sense. HOT 2
- Feature Request: "best observed" parameters for "best" classification output on test data and some accompanying commentary on why.
- [Question] On playground the parameter in entry are x and y, what about color ? HOT 1
- New Feature Request - Live update of weights upon placement of cursor on any weight HOT 1
- Model Compression
- Bug in UI
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from playground.