Feynman Liang
Feynman Liang
Summary: This is a demonstration of compiling a Python function to MLIR to LLVM IR to machine code then executing the program with the input from python. It is effectively...
### Issue Description When other RVs are concatenated together using `torch.stack`, `BMGInference` fails to trace execution because it assumes that all arguments to `stack` are of type `Tensor`. The example...
**Repro**: https://github.com/facebookresearch/beanmachine/pull/954#discussion_r691447200 **Expected**: Calling `summary()` returns a dataframe of summary statistics **Actual**: ``` RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans...
### Issue Description Applying an `AffineTransform` which shifts by +1 to a U[0,0.1] distribution should produce a U[1, 1.1] distribution. However, it appears that the samples being produced are all...
"createMemo function for completedTasks" is referenced in the narrative - this PR adds it to the code example.
This static attribute https://github.com/stefanwebb/flowtorch/blob/master/flowtorch/bijectors/affine_autoregressive.py#L18 is a global singleton and leaks across runs. To repro unexpected behavior: * Train an `AffineAutoregressive` against a 2D distribution (`default_param_fn.permutation` gets set to a size...
``` d, param = flowtorch.bijectors.AffineAutoregressive( flowtorch.params.DenseAutoregressive() )(dist.Independent(dist.Normal(torch.zeros(3), torch.ones(3)), 1)) d.rsample((10,2)).shape ``` should return the same `[10,2,3]` shape as `dist.Independent(dist.Normal(torch.zeros(3), torch.ones(3)), 1).rsample((10,2)).shape`, but it currently RuntimeErrors due to mismatched shape.
@stefanwebb - [ ] Add user docs on shape information, constraints, and bijector interface (CC @fritzo on PR) - [ ] Integrate constraint and `{forward,reverse}_shape` methods from torch transforms; put...
Using a batch_shape=[] and event_shape=[] base/target results in a shape mismatch RuntimeError ``` import torch import torch.distributions as dist import flowtorch import flowtorch.bijectors as bijectors # Lazily instantiated flow plus...
When I run the example on flowtorch.ai with a 1D distribution: ``` import torch import torch.distributions as dist import flowtorch import flowtorch.bijectors as bijectors # Lazily instantiated flow plus base...