detectron2.model_zoo

Model Zoo API for Detectron2: a collection of functions to create common model architectures listed in MODEL_ZOO.md, and optionally load their pre-trained weights.

detectron2.model_zoo.get_checkpoint_url(config_path)[source]

Returns the URL to the model trained using the given config

Parameters

config_path (str) – config file name relative to detectron2’s “configs/” directory, e.g., “COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml”

Returns

str – a URL to the model

detectron2.model_zoo.get(config_path, trained: bool = False, device: Optional[str] = None)[source]

Get a model specified by relative path under Detectron2’s official configs/ directory.

Parameters

  • config_path (str) – config file name relative to detectron2’s “configs/” directory, e.g., “COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml”

  • trained (bool) – see get_config().

  • device (str or None) – overwrite the device in config, if given.

Returns

nn.Module – a detectron2 model. Will be in training mode.

Example:

from detectron2 import model_zoo
model = model_zoo.get("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml", trained=True)
detectron2.model_zoo.get_config_file(config_path)[source]

Returns path to a builtin config file.

Parameters

config_path (str) – config file name relative to detectron2’s “configs/” directory, e.g., “COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml”

Returns

str – the real path to the config file.

detectron2.model_zoo.get_config(config_path, trained: bool = False)[source]

Returns a config object for a model in model zoo.

Parameters

  • config_path (str) – config file name relative to detectron2’s “configs/” directory, e.g., “COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml”

  • trained (bool) – If True, will set MODEL.WEIGHTS to trained model zoo weights. If False, the checkpoint specified in the config file’s MODEL.WEIGHTS is used instead; this will typically (though not always) initialize a subset of weights using an ImageNet pre-trained model, while randomly initializing the other weights.

Returns

CfgNode or omegaconf.DictConfig – a config object