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

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

Create a linear module.

Zero out the parameters of a module and return it.

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

x: (N, L, patch_size) imgs: (N, 1, num_voxels)

A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])