Subscribe
Sign in
Lobe 2.0 โ Machine learning made easy
Lobe helps you train machine learning models with a free, easy to use app. Just show it examples of what you want it to learn, and it automatically trains a custom machine learning model that can be shipped in your app. No code or experience required.
103
Replies
Lalo
Congrats on the launch! Crazy to see all these specialized tooling built around ML, and more coming from a huge player like Microsoft.
Share
@lalo thanks so much! We're excited to make machine learning more accessible :)
Thank you @moproduct for the hunt.
Hey everyone - we are excited to introduce Lobe, a new app from Microsoft!
Lobe is a free, easy to use desktop app for creating custom machine learning models. No coding or data science experience needed. We believe machine learning should be a tool usable by anyone, not just a small group of experts.
Lobe helps you through every step of the process. Collect and label your images quickly. Train models for free on your own computer without uploading your data to the cloud. Play with your model and improve it by providing feedback. Ship and use your model on any platform.
Thanks for checking us out - we are excited to see what you create with Lobe! We would love to get your feedback and are happy to answer any questions here.
https://lobe.ai
@mbeissinger hey Markus, thanks for this great product !
2 quick questions:
1/ can we use the trained model in another application ? How ?
2/ what's the pricing?
Thanks !
@b_maurin yes you can use the trained model in a variety of places -- we export to the standard formats of integration like Tensorflow, TFLite, and CoreML (https://docs.lobe.ai/docs/export...).
We also have some starter projects in code for running on mobile, the web, or spreadsheets of image URLs in our GitHub: https://github.com/lobe/
Lobe is free and runs locally on your computer :)
Hi @moproduct @mbeissinge!
Wooooowwwww! I am amazed, so easy to train and ship ML Models, I just saw the drinking water example and I was so shocked! This is the future! Kudos to the team for creating such a great product! Wow! Congratulations!
This is amazing! I've been trying to identify UI components for Landingfolio.com & gave up because ML is hard.
This app makes it unbelievably easy! Can't wait to integrate it to automate my workflow. It's already predicting the difference between hero, feature & header components 100% accurate ๐ฅ
@dannypostmaa wow, I love this idea. I started doing something similar with typography, I have a model with +1500 images that tells you the difference between different type categories. Canโt wait to check out your project.
@dannypostmaa @ramongilabert I don't think I can post links in here, but if you search on Twitter for lobe_ai, there is a person that did a model classifying Hebrew letters as well.
What I did to create the serif/sans serif/traditional/grotesque/etc. dataset was to add artboards of a good size in Sketch, take 20 or 30 different fonts, and put all the letters I could. After you create the first row, you can duplicate it and change the type pretty easily. I ended up with around 2000 images in pretty much no time.
Amazing execution for a very complex product!
What is your plan/roadmap for other functionality you want to ship? It looks like many pieces from V1 were cut off
@the_andriy_bond hey Andrew! :) We are planning on adding object detection in the near future, and we are planning on complementing the future set that you can see in lobe.ai.
Other, more complex functionality, like the ability to edit the graph, or even build your own, may come in the future.
@the_andriy_bond out of curiosity, which pieces from v1 particularly appealed to you?
@mbeissinger quick question regarding the personal trainer example in lobe.ai website. Are you guys converting to skeletal figure e.g. using postnet before training and inference or it's purely based on the image?
@ethanyfan hey Ethan! We are purely using image classification, and have built a similar example counting pushups as well with Lobe. You're thinking in the right direction though - in the future we would love to have the model architecture chosen based on a more detailed understanding of what your data represents.
@ethanyfan @mbeissinger itโll be great to have that option, but for many scenarios simple image classification gets the job done faster and more easily. Helping guide people in decisions like this will be an interesting challenge!
Amazing, I tried it and created a COVID or NOT training with X-Ray photos, it is remarkable, you all made it so simple to use!
I used v1 of this product and it was so awesome. It lived up to all its claims, super easy to use, super easy to integrate. So awesome Microsoft swiped them right up. I'm really excited for this v2.
@johnbhiggins let us know when you use version 2! This one is available to download right away at lobe.ai
@johnbhiggins @ramongilabert I'm sure the answer is "can't say" but will this be replacing azure machine learning studio (another product I love)? I recently saw in the serp title that that "(Classic)" was appended to the end of the title.
@johnbhiggins @ramongilabert you are right, the answer is I can't say ๐ but I wouldn't worry too much about that.
@johnbhiggins @ramongilabert a revised version of that product recently became Generally Available as Azure ML Designer and it is still alive and well! Pretty different from Lobe. Try them both!
@prakharshivam it's been a long time coming, this release. We started working on it over 2 years ago after being acquired by Microsoft.
Your team's hard work is definitely showing up in the product so far. I wish that you guys innovate a lot ahead too.
This is the future, I can see the light of this app. Congrats on such an amazing app.
Noice! Amazing how you've made ML modelling so accessible! ๐ค
Looking forward to see you expand it's scope! ๐ง
Any rough ETA on object and data classification?
@aidy_love thank you! We are working on object detection as we speak, and we hope to bring it really soon. I can't give you an estimated time yet, but know that we are really committed to it. Data classification comes after, though the foundation for it has been built ๐
@ayoolajohn_ thank you! We've been hard at work for the past 18 months trying to simplify the process of building a model as much as possible, so anyone can have access to this amazing technology! ๐
This looks way different from the first version that was launched some time back, why did you guys remove all the complexity ?
@gauthamzzz We wanted to focus first on accessibility and making the end-to-end process of working with ML simple and understandable to non-experts, and then expand capabilities after this first version. Many people struggled with the more advanced features initially, so we streamlined the complex model building and training processes using automated techniques. We still want this to be a powerful tool for working with ML and are looking to explore how to layer in more advanced capabilities later.
@ivan_zenkovich Thanks Ivan! Means a lot (: let us know if you need help when trying it out!
Can't wait for the text, tables and number functionality. Just started exploring AutoML for some datasets.
Love that you can easily highlight multiple images and label a bunch with the same label. It definitely seems to struggle on Mac if you import a large number of images to label in one go.
@ay8s thanks Andrew! are you having issues labeling large numbers of images on Mac with Lobe?
A few tips:
1. You can drag in a folder of organized images and Lobe will automatically label them for you (folder name = "Cats" with 500 images, they will all be labeled "Cats")
2. I see you're an iOS dev :) We have an iOS bootstrap app on GitHub to make it super easy to export a trained model to an iOS app! https://github.com/lobe/iOS-boot...
Let us know what you think!
If there are only two labels like Drinking, Not Drinking I wonder if the UI for labelling could be optimized to simply be a Checkmark/Cross like the Play section. That way it would be even fewer clicks to label more images.
@cohenjacobd Thanks, will take a look. I imported a unorganized folder of about 8000 images so I'm not surprised it had a few issues. A few images didn't import successfully so the failed dialog showed up but it was pretty sluggish showing/dismissing. Looks awesome though! :)
@ay8s thanks for the comment Andrew! And yes, we are really excited about that, too.
We are working on performance to support larger datasets as we speak as well! Stay tuned on our Twitter channels or on lobe.ai ๐
@cohenjacobd @ay8s ahh got it okay good to know! Today we support PNG, JPG, BMP, and WEbP formats. What image formats are you importing?
We will be adding support for more formats over time. You can learn more from our docs here and get tips for training a model and exporting too! https://docs.lobe.ai/docs/welcom...