Hi everyone,
I’ve always struggled with the 'friction' of calorie tracking. Most apps require you to search for every single ingredient, weigh it, and log it manually. It usually takes me 5-10 minutes per meal, which led me to quit every single time.
As a dev, I thought: Why can't I just take a photo and let AI do the heavy lifting?
I spent the last few months training a model to not just recognize a 'Salad', but to identify the components: the cherry tomatoes, the parmesan, the croutons, etc. It then estimates the volume and gives a macro breakdown.
It’s still in the early stages, but it has completely changed how I track my nutrition. I'm looking for some 'power-users' who are tired of manual logging to help me test this and tell me where it fails.
What do you think? Is photo-recognition the future of nutrition or is manual weighing still king for you?
[link] [comments]