AI Tech Suite

Platform.ai

Click to visit website

About

Platform.ai is an end-to-end codeless AI model platform specifically designed for computer vision applications. It provides domain experts with an intuitive point-and-click visual system that allows them to build computer vision models without needing deep learning knowledge. The platform is resource-light, reducing the need for data scientists, and employs a scalable 'label-as-you-go' strategy enabling the training of models with minimal initial labels. It streamlines the development process into simple visual tasks, leading to faster deployment and human-in-the-loop iterative development for improved model performance. The platform also offers various pricing plans catering to different project sizes and includes enterprise support.

Features

• human-in-the-loop iterative development

• codeless ai model development

• point-and-click visual system

• enterprise model deployment support

• scalable labeling strategy

FAQs

Once I train a model, what can I do with it?

Once a model is trained by platform you can use it to predict unlabelled images. This can be done via csv download or using a prediction API.

How do I upload a large set of images?

You can upload small collections (<10k images) right from your browser; larger collections can be imported from a GCS bucket.

How fast are predictions?

Our prediction API can be used in two modes, online or batch; the average latency for online is 150ms, the throughput on batch is typically 10k images per minute.

How many images do I need to label before I have a useful model?

The answer depends on the characteristics of your dataset and the machine learning task, but typically 100–500 examples per class are enough to train a model.

Can I deploy on-premise?

Enterprise customers can deploy models on-premise for prediction. Contact us for further details.

Can I use platform to do something other than classification?

Platform currently supports only multiclass and multi-label classification out of the box but can adapt the environment for other tasks depending on enterprise requirements.