Trenton Bricken
Trenton Bricken
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...
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.
In the install section of the readme please consider adding in something about having TensorFlow probability. I have spent too much time trying to install Edward2 and its dependencies by...
Would it be possible to add example code in for Discrete Flows like the demo examples from the paper? Eg. the discretized mixture of gaussians? I am finding that the...
Would it be possible to share a link to the research or reasoning behind the `soft_to_angle` Module for someone new to structural protein problems? My current hunch is that you...
I was wondering why you commented out the drmsd component of the loss function while training?
I am running `controllertrain.py`on a google cloud VM headlessly with python 3.7 and xvfb. Everything works but I have noticed what seems to be a linear relationship between the number...
It is noted here: https://github.com/numenta/nupic.research/issues/637 that we should not use the flag run_without_ray_tune but is there a way this can be fixed? I'm using a slurm server that is not...
I am trying to make an autoencoder that uses variable length inputs (batched together). I want to have `decoder=True` so that the decoding portion has the latent space as an...
Similar to this issue: https://github.com/farizrahman4u/recurrentshop/issues/61 But it seems like we should either have teacher forcing or read_out on at either time. Is there a way to transition between them? It...