At Scale we built a tool for model debugging in computer vision called Nucleus (scale.com/nucleus) designed exactly for this, which is free try out if you're curious to see where your model predictions are most at odds with your ground truth. Source: over 2 years ago

To address your point about gathering edge cases, which can also be defined as cases of low model fidelity for our use cases, there is active learning and tools such as Aquarium Learning and Scale Nucleus which make it easy to implement into workflows. Source: almost 3 years ago

AWS provides various services for Machine Learning and Artificial Intelligence, including Amazon SageMaker, AWS DeepLens, AWS DeepComposer, Amazon Forecast and more. Familiarize yourself with the services available to determine which ones suit your specific needs. - Source: dev.to / 5 months ago

Take a look at AWS deeplens. You might be able to make something work out of it. https://aws.amazon.com/deeplens/. Source: over 1 year ago

AWS DeepLens - Deep learning enabled video camera for developers - AWS (amazon.com). - Source: dev.to / over 2 years ago

So Amazon has this thing called Deep Lens. Https://aws.amazon.com/deeplens/ Basically, it's a really dinky computer with all the things needed to do Machine Learning with image recognition. It comes with several projects that all are about how to program it, and how to run machine learning enabled image recognition projects (including 'Hotdog-Not A Hotdog'!). It's an expense, but it would enable what you're... Source: over 2 years ago

AWS DeepLens is a hardware offering from AWS. It comes with a fully programmable camera you can use to train Machine Learning models for your specific task. Tutorials and guides also accompany this to get started right away. - Source: dev.to / over 3 years ago