nn

Modules

Sequential(layers[, holomorphic])	A sequence of equinox.Module applied in order similar to Sequential in Equinox.
RawInputLayer()	The layer that takes not only the output of the previous layer, but also the raw input basis state.
RefModel()	The model that allows accelerated forward pass through local updates and internal quantities.

Activation function

sinhp1_by_scale(x)	\(f(x) = \sinh(x) + 1\).
prod_by_log(x)	\(f(x) = \prod x\).
exp_by_scale(x)	\(f(x) = \exp(x)\).
exp_by_log(x)	\(f(x) = \exp(x)\).
pair_cpl(x)	\(f(x) = x_1 + i x_2\) , where \(x = (x_1, x_2)\).

Initializers

apply_lecun_normal(key, net)	Apply the Lecun normal initializer.
apply_he_normal(key, net)	Apply the He normal initializer.
apply_glorot_normal(key, net)	Apply the Glorot normal initializer.

Sign structures

compute_sign(kernel, s, output[, neg])	Compute the sign, phase, or cosine value based on the provided kernel and spin configuration.
marshall_sign(s)	Marshall sign rule for bipartite lattices.
stripe_sign(s[, alternate_dim])	Stripe sign rule for bipartite lattices.
neel120_phase(s)	120 degree Neel phase for triangular lattices.

Conv layers

ReshapeConv(dtype)	Reshape the input to the shape suitable for convolutional layers.
ConvSymmetrize([symm])	Symmetrize the output of a convolutional network according to the given symmetry.

Fermions

fermion_idx	Get the indices of occupied fermion sites.
changed_inds	Get the indices of the hopping fermions.
permute_sign	Get the sign change due to fermion hopping.