This is the standard forward function for non-distributed batch norm

Get Network Architecture based on arguments provided

Network is a GSCNN network

Load weights from snapshot file

test for function log_det_by_cholesky()

get map pairs Args: labels_4D : labels, shape [N, C, H, W] probs_4D : probabilities, shape [N, C, H, W] radius : the square radius Return:

get map pairs Args: labels_4D : labels, shape [N, C, H, W]. probs_4D : probabilities, shape [N, C, H, W]. radius : The side length of the squa

Constructs a ResNet-152 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-34 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Setup Data Loaders[Currently supports Cityscapes, Mapillary and ADE20kin] input: argument passed by the user return: training data loade

Calculate class centroids for all classes for all images for all tiles. items: list of (image_fn, label_fn) tile size: size of tile r

Wrap the network in Dataparallel