vis4d.zoo.faster_rcnn.faster_rcnn_coco

Faster RCNN COCO training example.

Functions

get_config()

Returns the Faster-RCNN config dict for the coco detection task.

get_sweep()

Returns the config dict for a grid search over learning rate.

get_config()[source]

Returns the Faster-RCNN config dict for the coco detection task.

This is an example that shows how to set up a training experiment for the COCO detection task.

Note that the high level params are exposed in the config. This allows to easily change them from the command line. E.g.: >>> python -m vis4d.engine.run fit –config configs/faster_rcnn/faster_rcnn_coco.py –config.params.lr 0.001

Returns:

The configuration

Return type:

ExperimentConfig

get_sweep()[source]

Returns the config dict for a grid search over learning rate.

The name of the experiments will also be updated to include the learning rate in the format “lr_{params.lr:.3f}_”.

Returns:

The configuration that can be used to run a grid

search. It can be passed to replicate_config to create a list of configs that can be used to run a grid search.

Return type:

ParameterSweepConfig