-
Dear developers:
I am trying to do HOSVD on a large image dataset. The dataset is arranged as (n_image, height, width ). The size of dataset is very large to about 40-50GB.
To my understanding, …
-
[`tensorly.decomposition.candecomp_parafac.normalize_factors`](https://github.com/tensorly/tensorly/blob/d82e08bc7434f63860efbc4287ffa425a84459ac/tensorly/decomposition/candecomp_parafac.py#L17) can p…
-
There is a two dimensional tensor a[m,n], and a three dimensional tensor b[k,n,h]. What API should I use to multiply two dimensional tensors by three dimensional tensors to get a three dimensional ten…
goljx updated
5 years ago
-
I want to prune resnet56, but when I use the example yaml in /examples/pruning_filters_for_efficient_convnets. I found that the it failed to create a thinning recipe ,and there is no filters moved.
I…
-
When I install tensorly in Colab with the following command:
`!pip install git+https://github.com/tensorly/tensorly.git`
And then import the sparse partial tucker like this:
`from tensorly.contrib.…
-
API for sparse tensors in TensorLy
============================
This thread is to discuss. collect opinions and thoughts about the best way to incorporate sparse tensors in TensorLy. @stsievert ha…
-
If I have a tensor of (30,40,50), and I want to expand it out to the first order, then I get a second order tensor of (30,2000), and I don't know if tensorflow has an API that implements it.
For e…
goljx updated
5 years ago
-
There is a two dimensional tensor a[m,n], and a three dimensional tensor b[k,n,h]. What API should I use to multiply two dimensional tensors by three dimensional tensors to get a three dimensional ten…
goljx updated
5 years ago
-
Hi all, nice project here.
I'd like to ask some questions about generalizing these algorithms to other classes that support the numpy.ndarray interface like [dask array](https://dask.pydata.org/e…
-
Running the `parafac` function in [this notebook from tensorly-notebooks](https://github.com/JeanKossaifi/tensorly-notebooks/blob/master/02_tensor_decomposition/cp_decomposition.ipynb) results in the …