Download a dataset. Parameters: save_path (str) -- A directory to save the data to. dataset (str) -- (opt

Load model from file. Args: path (str): file path

Make models eval mode during test time

save the current content to the HMTL file

(1) add_new_node(G, node) : add "node" to graph "G" (2) add_new_edge(G, node_a, node_b) : add edge "node_a--node_b" to graph "G" (3) exce

Initialize the GANLoss class. Parameters: gan_mode (str) - - the type of GAN objective. It currently supports vanilla, lsgan, an

Merge pre BN to reduce inference runtime.

(2) clear_node_feat(G, *fts) : Clear all the node feature on graph G. (6) get_cross_nes(x, y) : Get the four cross neighbors of pixel(x, y).

Init. Args: scale_factor (float): scaling mode (str): interpolation mode

Return visualization images. train.py will display these images with visdom, and save the images to a HTML

Projector MLP Args: in_features (int): input channels out_features (int): output channels mlp_dim (int, o

Inference interface for the model with padding augmentation Padding augmentation fixes the boundary artifacts in the output depth map

Insert a header to the HTML file Parameters: text (str) -- the header text

add images to the HTML file Parameters: ims (str list) -- a list of image paths txts (str list) -- a list of image

Builds a model from a config. The model is specified by the model name and version in the config. The model is then constructed using the build_from_c

Converts a depth map to a color image. Args: value (torch.Tensor, numpy.ndarry): Input depth map. Shape: (H, W) or (1, H, W) or (1, 1, H,

1x1 convolution

3x3 convolution with padding

Initialize our parser with basic options(only once). Add additional model-specific and dataset-specific options. These options are def

Main entry point to get the config for the model. Args: model_name (str): name of the desired model. mode (str, optional): "train