quantax.model.Triangular_ResSum

quantax.model.Triangular_ResSum(nblocks: int, channels: int, use_sinh: bool = False, trans_symm: ~quantax.symmetry.symmetry.Symmetry | None = None, dtype: ~numpy.dtype = <class 'jax.numpy.float32'>)

The ResSum equivalence for Triangular and TriangularB lattices. The kernel size is fixed as \(3\times3\).

Parameters:

• nblocks – The number of residual blocks. Each block contains two convolutional layers.

• channels – The number of channels. Each layer has the same amount of channels.

• use_sinh – Whether to use SinhShift as the activation function in the end. By default, use_sinh = False, in which case the combination of pair_cpl and Exp is used.

• trans_symm – The translation symmetry to be applied in the last layer, see ConvSymmetrize.

• dtype – The data type of the parameters.