Freezes all the parameters of all the ModuleDicts children that are exclusively used for the given bin configuration

Parameters for depthmap generation

Learning rate configuration for different layers of the model Args: lr (float) : Base learning rate Returns:

Return the static method <modify_commandline_options> of the dataset class.

Return the static method <modify_commandline_options> of the model class.

Get path where results are saved by default

Return a learning rate scheduler Parameters: optimizer -- the optimizer of the network opt (option class) -- stores all

Builds and returns a trainer based on the config. Args: config (dict): the config dict (typically constructed using utils.config.get_conf

ViT weight initialization, original timm impl (for reproducibility)

ViT weight initialization, original timm impl (for reproducibility)

Inverse attractor: dc = dx / (1 + alpha*dx^gamma), where dx = a - c, a = attractor point, c = bin center, dc = shift in bin center This is the def

Load checkpoint.

Load the specified network. Args: device (device): the torch device used model_path (str): path to saved model model_type

create empty directories if they don't exist Parameters: paths (str list) -- a list of directory paths

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Add new model-specific options, and rewrite default values for existing options. Parameters: parser -- original option p

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Modification of timm.models.layers.patch_embed.py: PatchEmbed.forward to support arbitrary window sizes.

Print the mean, min, max, median, std, and size of a numpy array Parameters: val (bool) -- if print the values of the numpy array

Print and save options It will print both current options and default values(if different). It will save options into a text file / [

Print and save options It will print both current options and default values(if different). It will save options into a text file / [

Return an image from the pool. Parameters: images: the latest generated images from the generator Returns images from th

para disp: disparity, [h, w] para rgb: rgb image, [h, w, 3], in rgb format

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

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

Constructs a ResNet-50 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet