Remove Lambda's about normalizing-flows HOT 6 CLOSED

Hi @gianmarcoaversanoenx,

I tried to reproduce the error you are describing, but for me saving and loading of models with MADE nets works fine with model.save and model.load no matter if preprocessing is a lambda function or not.
Can you provide a code snippet to reproduce this error, please?

Best regards,
Vincent

from normalizing-flows.

n_flos: int
dim: int
n_layers: int
hidden_units: int
for _ in range(n_flows):
                flows += [
                    normflows.flows.AutoregressiveRationalQuadraticSpline(
                        dim,
                        n_layers,
                        hidden_units,
                    )
                ]
                flows += [normflows.flows.LULinearPermute(dim)]
# Set base distribution
base = normflows.distributions.DiagGaussian(dim, trainable=False)
# Build flow model
nf = normflows.NormalizingFlow(base, flows)

# Save
torch.save(nf, 'model.ckpt`)

This would give me: Can't pickle MADE.<local>(lambda)...

from normalizing-flows.

Hi @gianmarcoaversanoenx,

thanks, I could reproduce the error now and replaced the lambda functions with something that can be pickled. Feel free to try it out yourself by installing the package from the current master branch.

Best regards,
Vincent

from normalizing-flows.

Thanks! :) Is this going to be pushed to PyPI, too?

from normalizing-flows.

Hi @gianmarcoaversanoenx,

sure, I will do so in about 1-2 weeks.

Best regards,
Vincent

from normalizing-flows.

I just released a new version of the package on PyPI. Hence, I'll close this issue.

from normalizing-flows.