Colorize depth maps.

Compute metrics for 'pred' compared to 'gt' Args: gt (numpy.ndarray): Ground truth values pred (numpy.ndarray): Predicted values

Generates normalmaps. :param depthmap: depthmap that will be used to generate normalmap :param pre_blur: apply gaussian blur before taking gra

Creates stereoscopic images. An effort is made to make them look nice, but beware that the resulting image will have some distortion. The corr

Crops the image according to the crop parameters. Args: image: RGB or depth image, shape (H, W, 3) or (H, W). crop_params: Crop p

Decode depth latent into depth map. Args: depth_latent (torch.Tensor): Depth latent to be decoded.

Reverses the imagenet normalization applied to the input. Args: x (torch.Tensor - shape(N,3,H,W)): input tensor Returns: tor

Returns a mask of edges in the depth map. Args: depth: 2D numpy array of shape (H, W) with dtype float32. Returns: mask: 2D numpy arra

Display current results on visdom; save current results to an HTML file. Parameters: visuals (OrderedDict) - - dictionary of imag

Encode RGB image into latent. Args: rgb_in (torch.Tensor): Input RGB image to be encoded. Retur

To ensemble multiple affine-invariant depth images (up to scale and shift), by aligning estimating the scale and shift

Automatically search for suitable operating batch size. Args: ensemble_size (int): Number of predictions to be ensembled inp

Run forward pass; called by both functions <optimize_parameters> and <test>.

Run forward pass; called by both functions <optimize_parameters> and <test>.

x_list contains a list of tensors to nest together and run

x_list contains a list of tensors to nest together and run

Get command line argument

Return traning losses / errors. train.py will print out these errors on console, and save them to a file

Helper to return a function object by name. func_name must identify a function in this module or the path to a function relative to the base '

Return the directory that stores images

Return image paths that are used to load current data

Intrinsics for a pinhole camera model. Assume fov of 55 degrees and central principal point.

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

Find and parse the .json config file for the model. Args: model_name (str): name of the model. The config file should be named config_{mo

Get prediction from the model currently loaded by the ModelHolder object. If boost is enabled, net_width and net_height will be ignored.