Flip image horizontally Parameters ---------- image : torch.Tensor [B,3,H,W] Image to be flipped Returns -------

Flip image horizontally Parameters ---------- image : torch.Tensor [B,3,H,W] Image to be flipped Returns -------

Post-process an inverse and flipped inverse depth map Parameters ---------- inv_depth : torch.Tensor [B,1,H,W] Inverse depth

Convert the model into training mode while keep layers freezed.

In distributed setting, this function only download checkpoint at local rank 0.

Post-process an inverse and flipped inverse depth map Parameters ---------- inv_depth : torch.Tensor [B,1,H,W] Inverse depth

Convert the model into training mode while keep layers freezed.

Upsample input tensor by a factor of 2

Upsample input tensor by a factor of 2

Upsample disp [H/4, W/4, 1] -> [H, W, 1] using convex combination

Upsample disp [H/4, W/4, 1] -> [H, W, 1] using convex combination

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Transform inputs for decoder. Args: inputs (list[Tensor]): List of multi-level img features. Returns: Tensor

Transform inputs for decoder. Args: inputs (list[Tensor]): List of multi-level img features. Returns: Tensor

Placeholder of forward function.

Placeholder of forward function.

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Check and initialize input transforms. The in_channels, in_index and input_transform must match. Specifically, when input_transform i

Check and initialize input transforms. The in_channels, in_index and input_transform must match. Specifically, when input_transform i

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Fuse inverse depth and flipped inverse depth maps Parameters ---------- inv_depth : torch.Tensor [B,1,H,W] Inverse depth map

Fuse inverse depth and flipped inverse depth maps Parameters ---------- inv_depth : torch.Tensor [B,1,H,W] Inverse depth map

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Initialize the weights in backbone and heads. Args: pretrained (str, optional): Path to pre-trained weights. Defa

Initialize the weights in backbone and heads. Args: pretrained (str, optional): Path to pre-trained weights. Defa