Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]

str: a "nice" summary string describing this module

Return an activation function given a string

merge dict `a` into dict `b` (non-inplace). values in `a` will overwrite `b`. copy first to avoid inplace modification

Forward function.

Args: x (float): Input images(BxCxHxW) axis (int): The index for weighted mean other_axis (int): The other index Re

Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and t

Convert the model into training mode while keep layers freezed.

return if the results is the best.

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

str: the string of the module

Computes the precision@k for the specified values of k

Useful args: - backbone: backbone name - lr_backbone: - dilation - return_interm_indices: available: [0,1,2,3],

Coerces input into a random number generator. If the input is None, then a global random state is returned. If the input is a numeric value,

Run per image evaluation on given images and store results (a list of dict) in self.evalImgs :return: None