pytorch-normalizing-flows

pytorch-normalizing-flows copied to clipboard

Loss becomes NAN with the Glow model

2

The loss for the Glow model becomes NAN (sometimes). I have only tested it with the half-moons dataset with the default model in the Jupyter notebook. Did not face the...

ashispati

Not a bug as much as an important note for MADE which are producing deltas on the input: For the output node where all of its input connections masked, the...

TrentBrick

Fixed bug with invertibility of AffineHalfFlow

2

I realized that the concatenation operation for the AffineHalfFlow is not correct given the even odd masking that occurs. I have implemented a simple fix for this.

TrentBrick

loss is negative

2

I just run a demo program, in which I would love to perform on these data:  Actually, blue points are real data(x) while red points are z. The prior...

jlian2

Different performance when using SlowMAF and MAF

1

Hi there, I have been using your Normalizing Flows codes for variational inference. When I use the two different flows: SlowMAF and MAF, the quality of these two results are...

XuebinZhaoZXB

Potential bug detected for high-dimension real NVP

1

I found the backflow of real NVP cannot reconstruct the original input data. This is caused by a bug in code when the dimension is more than 2: https://github.com/karpathy/pytorch-normalizing-flows/blob/b60e119b37be10ce2930ef9fa17e58686aaf2b3d/nflib/flows.py#L108 https://github.com/karpathy/pytorch-normalizing-flows/blob/b60e119b37be10ce2930ef9fa17e58686aaf2b3d/nflib/flows.py#L122...

kfzyqin

2D -> ND

2

Thanks for sharing a fairly complete repo of NFs. What kind of assumptions the code considers in the case of 2D that does not hold in ND? I have a...

sadegh-aa

Which Pytorch version do you use?

SafaMessaoud

Take the forward function in the Affineflow class as an example. x0 is constructed by x[0], x[2], x[4],..., and x1 is constructed by x[1], x[3], x[5], ..... But z is...

zhengqigao