Sets model to evaluation mode

Sets model to evaluation mode

Return tuple of list of paths containing the nonstatic scenes Arg(s): inputs : tuple(list[str]) image paths

Forwards the inputs through the network Arg(s): image0 : torch.Tensor[float32] image at time step 0

Forwards the inputs through the network Arg(s): image : torch.Tensor[float32] N x 3 x H x W image

Forwards the inputs through the network Arg(s): image0 : torch.Tensor[float32] image at time step 0

Forwards the inputs through the network Arg(s): image : torch.Tensor[float32] N x 3 x H x W image

Freeze a portion of the network Arg(s): module_names : list[str] spatial_pyramid_pool, encoder, decoder_

Computes gradients in the y and x directions Arg(s): T : torch.Tensor[float32] N x C x H x W tensor Returns:

Computes gradients in the y and x directions Arg(s): T : torch.Tensor[float32] N x C x H x W tensor Returns:

Computes gradients in the y and x directions Arg(s): T : torch.Tensor[float32] N x C x H x W tensor Returns:

Load depth Arg(s): depth_path : str path to depth map Return: numpy[float32] : depth map (1 x H x W)

Load images from image triplet Arg(s): path : str path to image triplet normalize : bool if set, nor

Convert a new tensor with the base-10 logarithm of the elements of x.

Logs summary to Tensorboard Arg(s): summary_writer : SummaryWriter Tensorboard summary writer

Logs summary to Tensorboard Arg(s): summary_writer : SummaryWriter Tensorboard summary writer

Logs summary to Tensorboard Arg(s): summary_writer : SummaryWriter Tensorboard summary writer

Returns the list of parameters in the model Returns: list : list of parameters

Restore weights of the model Arg(s): checkpoint_path : str path to checkpoint optimizer : tor

Loads weights from checkpoint and loads and returns optimizer Arg(s): restore_path : str path to model w

Restore weights of the model Arg(s): checkpoint_path : str path to checkpoint optimizer : to

Save weights of the model to checkpoint path Arg(s): checkpoint_path : str path to save checkpoint

Save weights of the model to checkpoint path Arg(s): checkpoint_path : str path to save checkpoint

Save weights of the model to checkpoint path Arg(s): checkpoint_path : str path to save checkpoint

Save weights of the model to checkpoint path Arg(s): checkpoint_path : str path to save checkpoint

Save weights of the model to checkpoint path Arg(s): checkpoint_path : str path to save checkpoint

Tilde (hat) operation Arg(s): v : torch.Tensor[float32] 3 element rotation vector Returns: torch.Tensor[floa

Inverse of the tilde operation Arg(s): R : torch.Tensor[float32] 3 x 3 inverse skew matrix Returns: torch.Te

Move model to a device Arg(s): device : torch.device device to use

Move model to a device Arg(s): device : torch.device device to use

Sets model to training mode

Sets model to training mode

Sets model to training mode

Sets model to training mode

Add noise to images Arg(s): images_arr : list[torch.Tensor[float32]] list of N x C x H x W tensors

Add noise to images Arg(s): images_arr : list[torch.Tensor[float32]] list of N x C x H x W tensors

Adjust brightness of an Image. Args: img (PIL Image): PIL Image to be adjusted. brightness_factor (float): How much to adjust th

Adjust brightness on each sample Args: images_arr : list[torch.Tensor] list of N x C x H x W tensors

Adjust contrast of an Image. Args: img (PIL Image): PIL Image to be adjusted. contrast_factor (float): How much to adjust the con

Adjust contrast on each sample Args: images_arr : list[torch.Tensor] list of N x C x H x W tensors

Adjust hue of an image. The image hue is adjusted by converting the image to HSV and cyclically shifting the intensities in the hue channel (

Adjust the each camera intrinsics based on the provided scaling factors and offsets Arg(s): intrinsics : torch.Tensor[fl

Adjust color saturation of an image. Args: img (PIL Image): PIL Image to be adjusted. saturation_factor (float): How much to adj

Adjust saturation on each sample Args: images_arr : list[torch.Tensor] list of N x C x H x W tensors

Backprojects pixel coordinates to 3D camera coordinates Arg(s): depth : torch.Tensor[float32] N x 1 x H x W depth map

Computes loss function Arg(s): output_depth0 : torch.Tensor[float32] N x 1 x H x W output depth for left

Computes loss function l = w_{ph}l_{ph} + w_{sz}l_{sz} + w_{sm}l_{sm} Arg(s): image0 : torch.Tensor[float32]

Computes loss function Arg(s): loss_func : list[str] loss functions to minimize target_depth