How to learn stuff outside of LLMs? I talked to my friends recently that told me they have their own image generation model, that's architecture agnostic and can work with Midjourney, StableDiffusion etc. But works on their GPUs. I have no idea what they're talking about. How can I start digging into the topic? I'd love to understand how startups like photoai.com or headshotpro.com managed to build their... Source: 8 months ago

The idea is to code up a website that will let brothers upload 10-20 of their pictures, and using AI will professionally generate AI headshots (like headshotpro.com quality), and put them all together in a nice composite layout ready for ordering prints. It would definitely be cheaper than hiring a photographer or an online service to come and handle it. Source: about 1 year ago

Of course, you can write your own code, in that case, think of it as an interactive matplotlib then! Also, it helps to mention we run a startup Datature, that is a no-code MLOps platform, hence explaining why we are focusing on removing the coding portion of this process :P. Source: almost 3 years ago

A while ago, we announced here that we built Datature and a bunch of users gave feedback and even built MaskRCNN models on our platform! However, we were sending collab updates back and forth - it was a mess. Hence we made Portal for any TensorFlow users to load TF2.0 models (any models off TF2 Model Hub works) and inspect your model visually on your dataset. Source: almost 3 years ago

If you'd like to train a tensorflow object detection model, you can check out https://datature.io - theres about 30 different models you can select from and you can add augmentation to your pipeline. Source: about 3 years ago

If you will be training an object detection model at the end, you can check out https://datature.io - you can annotate your data in browser (no installation) and train an object detection model + deploy when you are done for free! Source: about 3 years ago

Feel free to try it out at https://datature.io - additionally, we are always looking out for feedback and feature requests. We are working more MLOps feature to support teams, so let us know of your thoughts :). Source: about 3 years ago