TensorNetwork

TensorNetwork copied to clipboard

update contraction tutorials

6

We now also have Glen's contractor. We should add a tutorial for that

mganahl

fix all pytorch tests

7

As of lately pytorch has complex number support. This means we have to fix the tests that were skipping pytorch on the ground that complex was not supported.

mganahl

Where is the code of "TensorNetwork for Machine Learning" for MNIST/FASHION MNIST?

10

Hi, I could not find the code of "TensorNetwork for Machine Learning" for MNIST/FASHION MNIST as example for Machine Learning. May I know where I can find the code in...

jiawen11

Fix `base` contraction

1

Deals with scalar tensors in the network, where `opt_einsum` may include a 1-element tuples in the `opt_path`. Current behaviour: This errs ```python import numpy as np import tensornetwork as tn...

y-richie-y

https://github.com/users/dpebot/achievements/pull-shark

ghost

Support real and imag at the backend level

13

alewis

Maintenance of this repository

3

I am interested in using this repository, but there are no contributions in the past two years. It seems as though this repository is not maintained anymore. Are you planning...

VolodyaCO

Bug for numpy backend ``sum`` method

3

See source in https://github.com/google/TensorNetwork/blob/master/tensornetwork/backends/numpy/numpy_backend.py#L607. ```python def sum(self, tensor: Tensor, axis: Optional[Sequence[int]] = None, keepdims: bool = False) -> Tensor: return np.sum(tensor, axis=tuple(axis), keepdims=keepdims) ``` Therefore, ``sum(tensor)`` raises error for ``tuple(None)``

refraction-ray

Adding a Lanczos to compute the exponential of a tensor. First step for a TDVP class.

jansendavid

Support pinv

13

We need `np.linalg.pinv`, in both the backends and on `Tensor`.

alewis