retinanet_resnet50_fpn_v2

torchvision.models.detection.retinanet_resnet50_fpn_v2(*, weights: Optional[RetinaNet_ResNet50_FPN_V2_Weights] = None, progress: bool = True, num_classes: Optional[int] = None, weights_backbone: Optional[ResNet50_Weights] = None, trainable_backbone_layers: Optional[int] = None, **kwargs: Any) → RetinaNet

Constructs an improved RetinaNet model with a ResNet-50-FPN backbone.

Warning

The detection module is in Beta stage, and backward compatibility is not guaranteed.

Reference: Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection.

retinanet_resnet50_fpn() for more details.

Parameters:

• weights (RetinaNet_ResNet50_FPN_V2_Weights, optional) – The pretrained weights to use. See RetinaNet_ResNet50_FPN_V2_Weights below for more details, and possible values. By default, no pre-trained weights are used.

• progress (bool) – If True, displays a progress bar of the download to stderr. Default is True.

• num_classes (int, optional) – number of output classes of the model (including the background)

• weights_backbone (ResNet50_Weights, optional) – The pretrained weights for the backbone.

• trainable_backbone_layers (int, optional) – number of trainable (not frozen) layers starting from final block. Valid values are between 0 and 5, with 5 meaning all backbone layers are trainable. If None is passed (the default) this value is set to 3.

• **kwargs – parameters passed to the torchvision.models.detection.RetinaNet base class. Please refer to the source code for more details about this class.

class torchvision.models.detection.RetinaNet_ResNet50_FPN_V2_Weights(value)

The model builder above accepts the following values as the weights parameter. RetinaNet_ResNet50_FPN_V2_Weights.DEFAULT is equivalent to RetinaNet_ResNet50_FPN_V2_Weights.COCO_V1. You can also use strings, e.g. weights='DEFAULT' or weights='COCO_V1'.

RetinaNet_ResNet50_FPN_V2_Weights.COCO_V1:

These weights were produced using an enhanced training recipe to boost the model accuracy. Also available as RetinaNet_ResNet50_FPN_V2_Weights.DEFAULT.

box_map (on COCO-val2017)	41.5
categories	__background__, person, bicycle, … (88 omitted)
min_size	height=1, width=1
num_params	38198935
recipe	link
GFLOPS	152.24
File size	146.0 MB

The inference transforms are available at RetinaNet_ResNet50_FPN_V2_Weights.COCO_V1.transforms and perform the following preprocessing operations: Accepts PIL.Image, batched (B, C, H, W) and single (C, H, W) image torch.Tensor objects. The images are rescaled to [0.0, 1.0].