All plans include access to the platform environment and the ability to create private collections.
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. However, we do adapt the environment for other tasks depending on the requirements of our enterprise customers.