We have extended the FsDet framework with a tool that dynamically generates datasets from annotation files and drives the training process.

The tool has the following features:

• Determine the base and novel classes from the provided annotations (for the novel classes only a subset may be used for training).
• Determine how many instances are available, and set up the k-shot n-way problem accordingly.
• Prepare model structures for novel only and combined base+novel finetuning by adjusting the layer sizes to match the number of classes in the different sets.
• If the number of samples strongly varies, set up multiple training problems to make best use of the data, and run multiple fine-tuning steps.

The tool currently supports annotations in COCO format. However, this does not mean that COCO is required as a base model, as long as the annotations are provided in this format.