!pip install -qU git+https://github.com/harvardnlp/pytorch-struct
!pip install -q matplotlib

import torch
from torch_struct import DependencyCRF, LinearChainCRF
import matplotlib.pyplot as plt
def show(x): plt.imshow(x.detach())

# Make some data.
vals = torch.zeros(2, 10, 10) + 1e-5
vals[:, :5, :5] = torch.rand(5)
vals[:, 5:, 5:] = torch.rand(5) 
dist = DependencyCRF(vals.log())
show(dist.log_potentials[0])

# Compute marginals
show(dist.marginals[0])

# Compute argmax
show(dist.argmax.detach()[0])

# Compute scoring and enumeration (forward / inside)
log_partition = dist.partition
max_score = dist.log_prob(dist.argmax)

# Compute samples 
show(dist.sample((1,)).detach()[0, 0])

# Padding/Masking built into library.
dist = DependencyCRF(vals, lengths=torch.tensor([10, 7]))
show(dist.marginals[0])
plt.show()
show(dist.marginals[1])

# Many other structured prediction approaches
chain = torch.zeros(2, 10, 10, 10) + 1e-5
chain[:, :, :, :] = vals.unsqueeze(-1).exp()
chain[:, :, :, :] += torch.eye(10, 10).view(1, 1, 10, 10) 
chain[:, 0, :, 0] = 1
chain[:, -1,9, :] = 1
chain = chain.log()

dist = LinearChainCRF(chain)
show(dist.marginals.detach()[0].sum(-1))