If you want your model to train 20x faster, continuously move your mouse up and down the far left menu, or open the outline and madly expand/collapse the options for a layer :D edit: turbo mode: keep v8 at full speed: function sleep(ms) {return new Promise(resolve => setTimeout(resolve, ms));}; while (true) {console.log(document.getElementsByClassName("content").length); await sleep(20)};
Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
41–50 of 51 posts
Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#42Earlier quoted context omitted.
Thanks! The frontend is made with React and Typescript, backend is AWS serverless
Thank you for the information! I've been wanting to deploy a proof of concept webapp (mainly for my portfolio) using Amazon's Sagemaker but my website building skills is pretty limited besides using something like Jekyll. Do you have any recommendations on an upper level web framework?
Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#43Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#44If you want your model to train 20x faster, continuously move your mouse up and down the far left menu, or open the outline and madly expand/collapse the options for a layer :D edit: turbo mode: keep v8 at full speed: function sleep(ms) {return new Promise(resolve => setTimeout(resolve, ms));}; while (true) {console.log(document.getElementsByClassName("content").length); await sleep(20)};
That would be really awesome. Do you have a source as to why this would work ?
On a really basic MNIST model, 784->32dense->10dense, batch size 100, I'm getting about 2 batches per second idle, and 20 batches per second after running the above snippet.
To anyone who actually knows anything about web dev, please correct me with a proper explanation.
Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#45Editing 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 currently doesn't happen at least on my screen.
Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#46Earlier quoted context omitted.
Thank you for the information! I've been wanting to deploy a proof of concept webapp (mainly for my portfolio) using Amazon's Sagemaker but my website building skills is pretty limited besides using something like Jekyll. Do you have any recommendations on an upper level web framework?
That was my first serverless app and really enjoyed it. It has some quirks but gets you up and running in no time. FYI I used serverless.com
Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#47Can you currently create the architecture and run a given dataset against it? That would be very cool...
Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#48A small suggestion: the audio on the demo video was poor quality and difficult to understand. Perhaps a better microphone or higher bitrate would help.
Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#49Earlier quoted context omitted.
That would be really awesome. Do you have a source as to why this would work ?
I'm using chrome, I think the javascript engine is slowing down because it doesn't detect enough user interaction/"load"? Obviously, I'm not a fulltime web/browser developer. Hit F12, open the console, and paste in that javascript, and it will continuously run at the elevated speed, as long as it's the active tab in the current window. Break the tab out into its own window, and it will run in the background at full s…
Re: Show HN: Deep Learning GUI to Create, Train and Visualize Models in a Browser
#50Super 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 currently create the architecture and run a given dataset against it? That would be very cool...