aai-institute / veriflow Goto Github PK
View Code? Open in Web Editor NEWNormalizing flows for neuro-symbolic AI
License: BSD 3-Clause "New" or "Revised" License
Normalizing flows for neuro-symbolic AI
License: BSD 3-Clause "New" or "Revised" License
deepcopy import missing
The custom implementation of the solve_triangular function is only necessary if onnx export is needed but is a performance bottleneck. We should make it optional to use the implementation in torch.linalg.
When sampling the norm distribution in sample we need to unsqueeze the dimensions when the device is set to gpu. However if the device is set to cpu this unsqueeze needs to be removed otherwise we will get the following error:
r = r.repeat(*[1 for _ in sample_shape], self.dim)
RuntimeError: Number of dimensions of repeat dims can not be smaller than number of dimensions of tensor
Implement convenience function for onnx support
Rename to veriflow
GPU utilization on coda machines is low (5-15%).
There is potentially a bottleneck somewhere
Calling to_onnx
on a flow with LU layers raises a NotImplementedError
. Reason is that the function linalg_inv
is not implemented in onnx
A possible workaround could be to export a surrogate model with precomputed inverse matrix instead.
HyperoptExperiment fails with NiceFlow on mps devices.
We should unify the class names, especially for the flow classes. Current names carry a lot of legacy baggage. Ideally, names are in line with package names.
Several experiment configs are outdated and cannot be run currently.
Implement a layer that replaces additive coupling with additive autoregression.
Apparently, DenseNN of pyro is slow???
Basic MNIST Experiment with training once with all flow architectures
There seems to be an inconsistency between manually sampling from the base distribution and pushing the result through the flow and calling the sampling method.
Implement LU layers as non url preserving layers
Proper handling of lists with atomic types during recursion
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.