v7 is created by AlexeyAB and WonKinYiu the authors of YOLOv4. Who took over YOLOv3 from the original author Joseph Redmon, after Redmon quit the CV industry due to ethical concerns.
Have you seen Roboflow Universe? They have thousands of projects from their community already labeled for download and use. I always start there when I want t to start a new model. Recently for my trash picking up robot I found a good litter dataset to start from. https://universe.roboflow.com/
Prizes are still TBD - most likely will be a mix of cash prizes and/or merch. We're planning a proper tournament launch with prize pool and streams ETA ~Dec. You can think of this as an early-access playground to get familiar with the environment, and share any tooling needs/feedback/bugs before we officially launch and lock-in the major game rules.
I'm a builder and lately I've focused on creating and supporting machine learning pipelines. Image Ingestion, Job Queues, Dashboards. I even created a course on it that has over 800 students. Looking for something that allows me to build or teach.
I think it would be good to try something different. First I would get them good at typing code. This way they will not have to think about typing and thinking, they can just think. Second I would figure out a way to get them used to the concepts of programing, like for loops, variables, ect.. by doing other tasks. For example run a soccer drill like a for loop so they are learning secondly. I think this might help with some kids giving up early since its hard. It should be a little easier since they will have some experience with the concepts since they have run the drill before. Hope this makes sense, good luck!
I'm not a professional but I built a pipeline for Makers Part List - It involves ingesting a video URL, converting the video into images, then storing the images in google storage. Once stored I trigger the model to classify the image. The images are then displayed to annotators who verify/relabel the images. Once I get enough new images the system creates a .csv and uploads it to googles autoML where it retrains my model.
My bottlenecks now are splitting the videos into images as its a very CPU intensive process. Implementing a queue here is my best choice I think.
I'm running the front and backend of the consumer site on Heroku. The meat of pipeline is hosted on a DigitalOcean High CPU Droplet. I use ffmpeg to extract images from the provided videos. I store everything in Google Cloud Storage and create references to each photo in Firestore. I use Firebase to power for the image verifying/labeling app I built. Its a simple app that presents the viewer with the image and the label that it was given. If its not correct they enter the correct label. I use a cloud function to move the images into an exportable format for autoML once a new image threshold has been hit. Testing is me using it and seeing if it is correctly identifying the objects.
