Returns: dict[str->ShapeSpec]

plot input image and its reuslts

plot input image and its reuslts

Get features from feature maps in `features_list` that correspond to specific point coordinates inside each bounding box from `boxes`.

modified from dn-detr. You can refer to dn-detr https://github.com/IDEA-Research/DN-DETR/blob/main/models/dn_dab_deformable_detr/dn_c

apply transformation to the image. crop the image ot 640 short edge by default

Removes small disconnected regions and holes in a mask. Returns the mask and an indicator of if the mask has been modified.

Sample point labels from ground truth mask given point_coords. Args: instances (list[Instances]): A list of N Instances, where N is

Return semantic segmentation predictions in the original resolution. The input images are often resized when entering semantic segmentor. Mo

Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with t

Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with t

Some backbones require the input height and width to be divisible by a specific integer. This is typically true for encoder / decoder

Convert the model into training mode while keep layers freezed.

Convert the model into training mode while keep layers freezed.

Convert the model into training mode while keep layers freezed.