-
If I understand it correctly, currently in `make_design_matrix`, event information passed in as `paradigm` *will* be convolved with the HRF, and values passed to `add_reg` will *not* be convolved. Con…
-
Anyone has interest to utilize the sparsity to accelerate DNNs?
I am working on the fork https://github.com/wenwei202/caffe/tree/scnn and currently, on average, achieve ~5x CPU and ~3x GPU layer-wi…
-
Hi, trying to learn spektral here. I can't seem to use ARMAConv:
def create_model(n_nodes, n_node_features, model_layers):
node_features_input = Input(shape=(n_node_features,), dtype=tf.float3…
-
the ConvNets are currently using strides, which is not supported by by sparse tensors.
We can either extract the values manually (as done in [spconv](https://github.com/traveller59/spconv/blob/master…
-
-
Hello. Thank you for your excellent work. I would like to know how you handle gaussians that fall on the same grid during sparse convolution.
-
## 🚀 Feature
The ability to force layer's weights to be sparse with some input mask so that for example a 1d convolution that has a weight matrix with mXn weights would have a sparse matrix of size m…
-
I was browsing through the graph convolution code and saw the [reduction code](https://github.com/tensorflow/graphics/blob/228472e31327635e80220a740f13d672252bec9f/tensorflow_graphics/geometry/convolu…
-
Update: I just took a gander at [the source code](https://github.com/RichieHakim/sparse_convolution/blob/7aea68f92c8516cbc148235d4243a898138d4270/sparse_convolution/sparse_convolution.py#L10) and foun…
-
Hi:
Thank you for your great work, we are currently working on deployment of 3D Sparse UNet, may I ask will sparse inverse convolution and concat be included in future libspconv release?