mindscience.common

`mindscience.common.AdaHessian`	The Adahessian optimizer, which performs optimization using second-order information from the diagonal elements of the Hessian matrix.
`mindscience.common.batched_hessian`	Calculate Hessian matrix of network model.
`mindscience.common.batched_jacobian`	Calculate Jacobian matrix of network model.
`mindscience.common.get_2d_sin_cos_pos_embed`	Construct 2D sine-cosine positional embeddings on a two-dimensional grid.
`mindscience.common.get_loss_metric`	Gets the loss function.
`mindscience.common.get_multi_step_lr`	Generate decay learning rate array of each parameter group by gamma once the number of epoch reaches one of the milestones.
`mindscience.common.get_poly_lr`	Generate polynomial decay learning rate array.
`mindscience.common.get_warmup_cosine_annealing_lr`	Calculates learning rate base on cosine decay function.
`mindscience.common.glorot_uniform`	Glorot uniform.
`mindscience.common.lecun_init`	Lecun init.
`mindscience.common.MTLWeightedLoss`	Compute the MTL strategy weighted multi-task losses automatically.
`mindscience.common.patchify`	Convert an image-like tensor into a sequence of flattened patches.
`mindscience.common.pixel_shuffle`	Applies a pixel_shuffle operation over an input signal composed of several input planes.
`mindscience.common.pixel_unshuffle`	Applies a pixel_unshuffle operation over an input signal composed of several input planes.
`mindscience.common.PixelShuffle`	Applies a pixelshuffle operation over an input signal composed of several input planes.
`mindscience.common.PixelUnshuffle`	Applies a pixelunshuffle operation over an input signal composed of several input planes.
`mindscience.common.RelativeRMSELoss`	Relative Root Mean Square Error (RRMSE) is the root mean squared error normalized by the root-mean-square value where each residual is scaled against the actual value.
`mindscience.common.SpectralNorm`	Applies spectral normalization to a parameter in the given module.
`mindscience.common.to_2tuple`	Convert an integer or a tuple of integers to a 2-tuple.
`mindscience.common.to_3tuple`	Convert an integer or a tuple of integers to a 3-tuple.
`mindscience.common.unpatchify`	Convert a sequence of flattened patches back into an image-like tensor.
`mindscience.common.WaveletTransformLoss`	The multi-level wavelet transformation losses.