Coupling layers

[vmoens]

Adds Coupling layers.

### Test plan

from flowtorch.parameters.coupling import DenseCoupling, ConvCoupling
from flowtorch.bijectors.coupling import CouplingBijector as Coupling, ConvCouplingBijector
import torch
torch.set_default_dtype(torch.double)

def test():
    d = DenseCoupling()
    c = Coupling(d)
    c = c(shape=torch.Size([32,]))
    for p in c.parameters():
        p.data += torch.randn_like(p)/10
    x = torch.randn(1, 32,requires_grad=True)
    y = c.forward(x)
    yd = y.detach_from_flow()
    x_bis = c.inverse(yd)
    torch.testing.assert_allclose(x, x_bis)
    
    torch.testing.assert_allclose(
        c.log_abs_det_jacobian(x, y), 
        c.log_abs_det_jacobian(x, yd)
    )
    
test()

[stefanwebb]

This is really fantastic - I think it's almost there! Let's have a chat offline about coupling transforms, I think there may be a few ways to interpret them from the literature

[codecov-commenter]

Codecov Report

Merging #92 (54b4078) into main (4992731) will increase coverage by 0.04%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main      #92      +/-   ##
==========================================
+ Coverage   98.25%   98.29%   +0.04%     
==========================================
  Files           6        6              
  Lines         229      235       +6     
==========================================
+ Hits          225      231       +6     
  Misses          4        4              

Flag	Coverage Δ
unittests	98.29% <100.00%> (+0.04%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
tests/test_bijectivetensor.py	98.64% <ø> (ø)
tests/test_bijector.py	100.00% <100.00%> (ø)
tests/test_distribution.py	100.00% <100.00%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 4992731...54b4078. Read the comment docs.