Appends a key-value pair to the hash table. Args: key (torch.Tensor): Key tensor of the form [c1, c2, c3, t].

Appends a key-value pair to the hash table. Args: key (torch.Tensor): Key tensor of the form [c1, c2, c3, t].

Appends a key-value pair to the hash table. Args: key (torch.Tensor): Key tensor of the form [c1, c2, c3, t].

Same as to in torch module Don't really underestand why this isn't a module in the first place

Performs a single optimization step.

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

Create a 1D, 2D, or 3D convolution module.

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take

Read and unpack the next bytes from a binary file. :param fid: :param num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc.

Sampling with CDFs from proposal networks. Args: prop_sigma_fns: Proposal network evaluate functions. It should be a list

Performs a single optimization step.

F.binary_cross_entropy is not numerically stable in mixed-precision training.