AiFiddle

AI

deep learning gui

SHOW HN2019

AiFiddle

Deep Learning GUI to Create, Train and Visualize Models in a Browser

beta.aifiddle.io

#deep learning#neural network#visual model builder#keras export

216points
44comments
#178of 2,195 in 2019
Top 9%of 2019 by points

How HN took it

MixedNo clear lean

10 positive, 8 neutral or asking, 5 mixed, 4 critical, out of 27 comments about the project. Thread score +0.18.

Idea: 6 for, 0 againstExecution: 0 for, 3 againstDesign: 1 for, 0 againstPerformance: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Useful as a teaching and prototyping tool

    From 3 comments
    • Really awesome and will be super helpful as a teaching aide for ML/Deep learning classes!
      vinayan3 on HN
    • Very nice concept. This has the potential to be a great teach / prototyping tool
      k4renio on HN
    • Super awesome! I had a similar idea about a year ago but never got to implement it. We need more visual and straightforward ways to create neural network architectures. Can you…
      edshiro on HN
  • Slick, well-done interface

    From 3 comments
    • This is so slick!
      samzer on HN
    • This is really well done. I've got to mention two missing features that I find important: 1 - help popups: it will be nice if terms had a small help icon that can display a…
      amitport on HN
    • What is the tech stack used for the website/app? Looks great btw.
      Rainymood on HN
  • Drawing digits and seeing recognition is fun

    From 1 comment
    • Wow this is great! Makes the process so much more interactive, being able to draw your own digits and it gets recognised is great. Some small issues I ran into for your todo…
      hacker_9 on HN

Objections

  • Layer icons are tiny and deleting layers is unclear

    From 1 comment
    • Cool, project - I really believe that we need more visual tools for building and debugging neural nets. I had a hard time figuring out how to delete a layer (the icons on the…
      WhiteNoiz3 on HN
  • Training errors and bugs reported

    From 3 comments
    • Really nice - really like it for just fiddling around with models. One missing feature would be an "undo" function - I accidentally deleted a layer and couldn't find a way to…
      mattlondon on HN
    • Yes please! I have no idea what I'm doing (ok only a little), and finally got the dimensions to match and have trainable layers, and now I am informed that 't.slice is not a…
      kaybe on HN
    • As I said, I don't really know what I'm doing.. The editor crashed while I was playing with it, so I remade the model here: (still the same error)…
      kaybe on HN
  • No mobile support

    From 1 comment
    • Hi, the message on mobile has two errors: "Appologies AiFiddle currently does not support mobile device. Do you want to get notified on futur updates ?" 'Apologies' and 'future'.…
      Nashooo on HN
  • Shape changes do not cascade through the graph

    From 1 comment
    • Editing a layer and changing the number of filters, stride or kernel size effectively changes the shape of that layer, but it should cascade a re-calculation down the path, which…
      glastra on HN

Requests

  • Export to Keras, PyTorch or TensorFlow code

    From 3 comments
    • Awesome work. Now make it emit keras/tf/torch code!
      bicubic on HN
    • Had the same idea; opened a "feature request" here: https://github.com/m4nuC/aifiddle-issues/issues/6 Not sure how easy it will be to support all the types of layers on all…
      ivan_ah on HN
    • Thanks for taking the time. Keras functional API export coming soon. The rest will follow.
      0mbre on HN
  • Custom dataset support

    From 3 comments
    • The demo video is very compelling! Do you support proprietary datasets? A small suggestion: the audio on the demo video was poor quality and difficult to understand. Perhaps a…
      abrichr on HN
    • Super awesome! I had a similar idea about a year ago but never got to implement it. We need more visual and straightforward ways to create neural network architectures. Can you…
      edshiro on HN
    • Thanks! Custom dataset indeed on the todo list. The feature is half done already, I should be able to release it soon.
      0mbre on HN
  • Export to Colab

    From 2 comments
    • This is super awesome! Being able to export this to colab would be amazing. I'm really looking forward to this feature! Are you willing to share which web framework you used to…
      syntaxing on HN
    • In the backlog. With export to Colab.
      m4nu on HN
  • Undo for deleted layers

    From 1 comment
    • Really nice - really like it for just fiddling around with models. One missing feature would be an "undo" function - I accidentally deleted a layer and couldn't find a way to…
      mattlondon on HN
  • Automatic reshape layers or suggestions

    From 1 comment
    • Cool, project - I really believe that we need more visual tools for building and debugging neural nets. I had a hard time figuring out how to delete a layer (the icons on the…
      WhiteNoiz3 on HN

Questions

  • Is the tech stack used?

    From 2 comments
    • What is the tech stack used for the website/app? Looks great btw.
      Rainymood on HN
    • I'm also interested in tech stack used. What are you using in the backend?
      pplonski86 on HN
  • Why visualizing the tensor flow matters

    From 1 comment
    • I'm not a machine learning engineer, so I'll ask the dumb question: why is visualizing this flow important? What's the benefit?
      ztratar on HN

Alternatives named

  • Google Colab

    From 2 comments
    • Anyone who is messing around with convolutional networks is almost guaranteed to have anaconda installed. The convenience of a few less clicks in exchange for platform lock-in is…
      bicubic on HN
    • I'd encourage everyone not to support colab or any other proprietary lock-in platforms. But do as you will.
      bicubic on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/19025709)