@@ -32,7 +32,7 @@ The package consists of the following operations with reduction types `"sum"|"me
...
@@ -32,7 +32,7 @@ The package consists of the following operations with reduction types `"sum"|"me
*[**segment_coo**](https://pytorch-scatter.readthedocs.io/en/latest/functions/segment_coo.html) based on sorted indices
*[**segment_coo**](https://pytorch-scatter.readthedocs.io/en/latest/functions/segment_coo.html) based on sorted indices
*[**segment_csr**](https://pytorch-scatter.readthedocs.io/en/latest/functions/segment_csr.html) based on compressed indices via pointers
*[**segment_csr**](https://pytorch-scatter.readthedocs.io/en/latest/functions/segment_csr.html) based on compressed indices via pointers
In addition, we provide the following **composite functions** which make use of `scatter_*` operations under the hood: :`scatter_std`, `scatter_logsumexp`, `scatter_softmax` and `scatter_log_softmax`.
In addition, we provide the following **composite functions** which make use of `scatter_*` operations under the hood: `scatter_std`, `scatter_logsumexp`, `scatter_softmax` and `scatter_log_softmax`.
All included operations are broadcastable, work on varying data types, are implemented both for CPU and GPU with corresponding backward implementations, and are fully traceable.
All included operations are broadcastable, work on varying data types, are implemented both for CPU and GPU with corresponding backward implementations, and are fully traceable.
